In today’s competitive online retail environment, shoppers expect fast, relevant, and personalized results and eCommerce businesses must keep up. To improve conversion rates and drive revenue, search managers and merchandisers need more than basic data, they need eCommerce search analytics that offer clarity into how shoppers engage with onsite search and navigation.
That’s why we built FindTuner Insights, a new feature designed specifically for eCommerce search managers and merchandisers. Unlike general-purpose web analytics tools, Insights surfaces granular, actionable data that shows how shopper behavior connects to search performance and business outcomes.
This is the first in a three-part blog series exploring how FindTuner Insights helps eCommerce teams uncover meaningful trends, optimize the onsite search experience, and drive measurable improvements. In this post, we introduce what FindTuner Insights does and why it matters. Upcoming articles will show how to use it effectively and how it complements tools like Google Analytics.
Closing the Search Analytics Gap
Most eCommerce sites rely on web analytics tools to understand user behavior however those tools weren’t designed with onsite search optimization in mind. They may show top search terms or click-through rates, but they rarely offer the depth needed to evaluate search merchandising strategies or understand the full path from search to purchase. FindTuner Insights fills this gap with search-specific analytics tailored to eCommerce. It gives merchandisers the visibility they need to understand which queries lead to conversions, which filters influence outcomes, and where hidden opportunities lie.
Built for Action, Not Just Observation
Rather than just displaying raw data, FindTuner Insights delivers actionable search analytics. It reveals patterns such as high-traffic search queries with low conversions or product placements that underperform. This allows merchandisers to focus their efforts where they will have the most impact, whether that’s improving relevance, promoting high-margin items, or refining filter logic. And because Insights is built directly into the FindTuner platform, it requires no setup, no custom configuration, and no waiting on analytics teams. Search managers and merchandisers can instantly access the data they need right when they need it.
Use Case: Promoting a High-Value Product Line
Let’s say an online retailer wants to increase sales of a specific footwear brand known for its high profit margins. The merchandising team uses FindTuner to elevate these products in search results, boosting them for relevant queries and applying targeted filters to help guide shoppers toward them. With traditional analytics tools, the team might notice that sales of the footwear brand have increased over the past few weeks. But they’re left guessing: Did the boost in search actually drive the sales? Are shoppers finding the products through search or arriving via other channels like email or paid ads? Are promoted products converting as expected—or are shoppers clicking but dropping off?
FindTuner Insights eliminates that guesswork.
By delivering search-specific attribution data, Insights shows exactly which search terms led shoppers to the promoted products, which filters were applied, and what actions those shoppers took next. It can reveal, for instance, that a large percentage of purchases for the brand came from searches that didn’t include the brand name, suggesting that boosting the brand for more generic queries (like “men’s running shoes”) is paying off.
Just as importantly, Insights can detect where strategies aren’t working. If shoppers are consistently seeing the boosted product but not clicking, or clicking but abandoning before purchase, merchandisers are alerted to a gap in the shopper journey. That may point to issues like irrelevant search placement, poor product images, or pricing concerns. Armed with this knowledge, the team can iterate quickly, testing new tactics with confidence and measuring their impact in real time.
In short, FindTuner Insights connects search merchandising strategy directly to shopper behavior and outcomes, helping eCommerce teams make smart, data-backed decisions that drive both performance and profitability.
Coming Up Next: A Deeper Dive into Insights
This overview only scratches the surface of what FindTuner Insights can deliver. In the next post, we’ll explore practical examples of how eCommerce teams are using Insights to fine-tune search performance, test new merchandising strategies, and measure their impact. If you’re ready to bring precision and clarity to your eCommerce search strategy, FindTuner Insights is here to help. If you are considering FindTuner, please please contact us for a demo today!
We are excited to announce that FindTuner 3.9 is immediately available! The new release delivers actionable search insights, empowering merchandisers to optimize shopper journeys, measure strategy impact, and drive revenue with data-driven eCommerce search analytics.
As online shoppers increasingly expect fast, relevant, and personalized experiences, ecommerce search managers and merchandisers are under growing pressure to optimize every aspect of the search journey. Yet many teams lack the visibility they need into how shoppers interact with onsite search and navigation—and how those behaviors translate into revenue. Traditional analytics tools often fall short, failing to connect shopper intent with the performance of merchandising strategies. That gap makes it difficult to uncover what’s working, what’s not, and where to focus next. FindTuner 3.9 bridges the gap with a purpose-built Insights feature that turns shopper behavior into clear, actionable guidance.
Actionable Insights that Drive Revenue and Efficiency
FindTuner Insights provides actionable analytics based on shopper behavior, helping merchandisers understand how shoppers interact with search and navigation as well as the impact of merchandising strategies. Insights highlight patterns such as top search terms, low-converting terms, and revenue by strategy or product. FindTuner Insights makes it easy for merchandisers to identify opportunities to optimize the search experience.
Key capabilities of Insights include:
Search-focused Analytics: FindTuner Insights delivers purpose-built analytics for eCommerce search, tailored specifically for [eCommerce search managers and] merchandisers. It provides immediate, self-serve access to data—no need to rely on analytics teams or dig through generic dashboards. With direct visibility into shopper behavior across search terms, filters, and navigation paths, merchandisers can quickly understand how shoppers explore and discover products.
Actionable Insights: Rather than just reporting data, FindTuner Insights pinpoints specific opportunities to improve the search experience. It surfaces trends like high-volume queries with low conversion rates or overlooked products with strong potential. These targeted insights help teams prioritize changes that drive measurable impact.
Insight Meets Action: FindTuner Insights provide a clear feedback loop between merchandising actions and shopper outcomes, enabling continuous optimization. Merchandisers can evaluate the performance of strategies through A/B testing, clickstream, funnel and cohort analysis. This makes it easy to understand what’s working, refine tactics, and demonstrate the effectiveness of search merchandising decisions.
If you are an existing client and would like to learn more about these new features, please contact your Deployment Consultant. If you are considering FindTuner, please please contact us for a demo today!
In the world of ecommerce, personalization is key — and that’s true not just when selling to individual consumers, but also in business-to-business sales. Although businesses are not persons, exactly, the ability to tailor search results to different buyers gives B2B sellers critical advantages for driving B2B sales.
Indeed, search personalization can be all the more important in the realm of B2B ecommerce given the complexity of B2B sales. Buyers may only be able to purchase certain products due to factors like regional product availability or contractual agreements, for example. By making it possible to integrate these considerations into search results, B2B search personalization helps enable smoother transactions for shoppers and increase revenue.
Here’s a look at what personalized search means in the context of B2B ecommerce, why it’s important and how to implement it.
What is B2B search personalization?
B2B search personalization is the ability to customize search results on ecommerce sites based on varying customer profiles and intents. It takes into account a range of factors — like a company’s purchasing history, the buyer’s location and pricing agreements made between the B2B seller and the company — to curate search results that best reflect the needs of a specific buyer.
In many ways, B2B search personalization is similar to personalized search results that a shopper might see in a business-to-consumer (B2C) context. But in the B2B world, personalized search is geared more toward a company’s customers as well as the individual employees at those companies who search for products. That said, individual employee preferences and past interactions can factor into B2B search personalization as well. For example, they can help generate search facets based on those a shopper used previously or enable a fast re-buy experience based on past purchasing decisions.
How personalized search benefits B2B eCommerce sellers
In the realm of B2B ecommerce, personalized search addresses several critical needs and challenges for B2B sellers.
Navigating complex product catalogs
B2B sellers might sell thousands, hundreds of thousands or millions of products. On top of that, the inventories can be quite complex. A bolt could be available in multiple lengths, diameters and materials, for example, leading to dozens of variations of the same product. Likewise, in some cases product descriptions include information aggregated from suppliers, which is not always consistent in structure or quality.
With such large and complex inventories, it can be challenging to ensure that shoppers see relevant search results accompanied by accurate information. If B2B sellers display products that are out of stock or show pricing information that doesn’t reflect agreements made with a specific buyer, the chance that a shopper will make a purchase decreases.
Search personalization helps here by allowing B2B sellers to customize results for each shopper. They could display only items that are available in the region where the customer is based, for example, or promote products that the company has purchased previously to the top of search results.
Contract-aware merchandising
In B2B contexts, it’s not uncommon for B2B sellers to make unique agreements with different customers. They might sign contracts that establish custom pricing or delivery time guarantees, for instance. They may also not agree to sell certain items to particular customers due to issues like the inability to support products in a customer’s region.
With personalized search, it’s possible to factor these details into search results. Rather than displaying generic product listings that may not be relevant or accurate for a specific buyer, each B2B customer sees results that reflect unique contractual agreements.
Buyer segmentation
As in B2C ecommerce, B2B buyers often fall into various segments in ways that impact how and what B2B companies sell to them. Some products may only be available to buyers in certain regions or countries, for instance. Similarly, product support or return policies may dictate which items a B2B seller can offer to different customers.
Here again, the ability to customize search results for each buyer is critical for ensuring that shoppers see information that is relevant and accurate for them.
Putting personalized search for B2B into practice
There are several techniques and approaches available for implementing B2B search personalization. Common strategies include:
Using machine learning and/or rules-based search merchandising to highlight products most relevant for specific customers. B2B sellers can also use these techniques to promote high-margin products, closeout items or other results they want to underscore.
Generating customized search facets to help shoppers navigate to products relevant to them. This is another area where machine learning can come into play by automatically parsing data like catalog selections and generating dynamic facets accordingly.
Implementing search autocomplete features to suggest search terms that reflect a customer’s purchasing history, contractual agreements and so on.
Using search results to promote related products that are likely to interest a buyer based on factors like company segmentation or product availability.
Implementing capabilities like these helps take B2B eCommerce to the next level. Instead of treating buyers as generic, anonymous entities, B2B sellers can address the unique context of each company they sell to, leading to a better experience for buyers and, in many cases, higher sales and revenue numbers.
Driving B2B success with personalized search
In the B2B space, purchasing decisions are often more complex than they are in the B2C world. B2B buyers are typically more focused on finding specific products, adhering to established contracts and ensuring supply chain continuity. Using B2B search personalization, companies can deliver relevant search results that reflect unique factors such as contractual agreements, purchasing histories and regional availability. In turn, they can streamline the buying process, reduce errors and strengthen customer loyalty.
Ultimately, this level of personalization helps B2B companies enhance the customer experience while driving higher conversion rates and encouraging repeat business — all of which are critical to success in today’s competitive digital marketplace.
Search merchandising for eCommerce search optimization
What makes eCommerce search successful? Part of the answer, of course, is deploying a solid search engine that can accurately interpret shopper queries and display results that customers find relevant.
But simply having a great search engine at your disposal is often not enough on its own to optimize the value that search brings to your eCommerce business. To take the power of search to the next level, online retailers must also be able to leverage techniques like search optimization and machine learning to deliver personalized search results that align with sales and marketing goals.
This is where search merchandising comes in. As we explain in this blog, search merchandising makes it possible to double-down on the value of search as a vehicle for enhancing the customer experience, boosting eCommerce conversion rates and maximizing business success.
What is search merchandising (searchandising)?
Search merchandising (also called searchandising) is the art and science of presenting search results in ways that account for relevancy, shopper intent and business objectives. The purpose of search merchandising is to call shoppers’ attention to specific items or types of items that the business wants to promote. Search merchandising works by taking the results generated by a search engine, then modifying them in some way that adds value. Examples include:
Personalizing search results by highlighting products that a specific shopper is most likely to find relevant based on their search and purchasing history.
Dynamically presenting facets and filters based on shopper context making it easier to find products.
Highlighting products that have a higher profit margin than other products. In this way, search merchandising would help the business boost its profitability.
Promoting closeout items to free up space for new stock. This strategy would help the company achieve its inventory management goals.
In short, instead of simply relying on the results generated by a search engine to determine how products are presented, search merchandising leverages analytics, shopper behavior and other contextual signals, along with marketing and sales goals, to enhance the effectiveness of search results.
How does search merchandising work?
Typically, search merchandising strategies are driven by a combination of three types of data. The first is information that reflects customer goals and intent, such as a shopper’s purchasing history and click-stream behavior. The second is data from backend systems that track revenue, margin, stock status, ratings and reviews, and availability (among others). The third is data associated with marketing and sales priorities, like products that the company wants to promote.
By configuring search to deliver results based on each type of insight described above, online retailers can ensure that each search generates results that are optimized for the needs of the business and shoppers.
Why is search merchandising important?
The main reason why ecommerce search merchandising is important is straightforward enough: Search plays a central role in helping shoppers find products on online shopping sites. By ensuring that search results align both with shopper preferences and marketing goals, search merchandising maximizes the value that search brings to eCommerce businesses.
To place those statements in context, let’s dive a bit deeper into the significance of search in eCommerce and why generic search results – meaning those that have not been merchandised – often fall short.
43 percent of visitors head straight for the search box when they open a website, and shoppers who use search functionality are more than twice as likely to purchase products as those who don’t. This means that the better your site’s search is at leading shoppers to relevant results, the more likely it is to drive sales and increase revenue.
Unfortunately, not all search engines are fully optimized for the task of connecting shoppers with the most relevant products and enabling business success. To achieve those goals, online retailers need search engines that are not only capable of interpreting shoppers’ intent accurately, but that can also tailor search results in ways that help support business goals.
The three pillars of effective search merchandising
With this approach, there is no need for employees to configure curation criteria manually each time the data changes. Instead, retailers can simply define overall goals – like increasing profit margins or aligning search results with marketing campaigns – and let the search engine customize each search result accordingly.
Merchandising Search Results with Human Touch
Merchandising search results with human touch brings a unique, shopper-centered perspective. By carefully selecting and promoting products and brands that resonate with shoppers, merchandisers can create more meaningful connections and guide shoppers toward the best options. This personalized approach allows online retailers to shape search results in ways that align with shifting preferences, seasonal trends, and brand identities. Doing so makes it possible to leverage search in support a variety of priorities, including:
Product promotions: Search merchandising can help businesses promote certain products that they want to prioritize. Just as important, it can bury or exclude others.
Personalized search results: Each shopper is unique. With search merchandising, retailers can dynamically optimize search results for individual shoppers based on data like purchasing history – as Migros did, for example, with help from FindTuner.
Shopper-specific results: Sometimes, as in B2B eCommerce, certain products may only be available to certain customers based on factors like the region the customer is located in or the type of relationship it has with the retailer. With search merchandising, eCommerce sites can ensure that the products each customer sees are actually available for that customer.
Collection-based merchandising: Effective search merchandising makes it possible to group certain products together. For instance, if you want to highlight products related to an upcoming holiday, you could tailor search results accordingly.
Optimizing the Shopper Experience
When implemented effectively, search merchandising can help optimize the overall shopping experience.
For example, a solid search merchandising tool can generate dynamic facets – meaning facets that are generated automatically based on the product data returned from a shopper’s query. Because dynamic facets reflect the unique context of each shopper’s journey, they can help with filtering search results and finding relevant products quicker. In turn, dynamic facets help to boost conversion rates and revenue.
Along similar lines, search merchandising enables facet customization, either by machine learning or human touch. For instance, a site could use machine learning to display facets that allow shoppers to sort product results based on brands they’ve purchased previously or price points that align with their prior purchasing behavior.
Search merchandising can also power visual navigation which helps shoppers find what they’re looking for faster. For instance, a search for “appliances” could provide a list of results with prominent visual elements that draw shoppers’ attention toward popular categories of appliances, while deemphasizing appliance types that may be of less interest.
Displaying banners helps capture shoppers’ attention and guide them toward specific promotions, products, or categories, enhancing their overall shopping experience. Banners can highlight special deals, new arrivals, or trending items, making it easier for them to discover relevant products and feel inspired to explore further. Strategically placed banners add a visual, curated layer to the search experience, encouraging higher engagement and driving conversions.
Through practices like these, search merchandising not only helps online retailers achieve their sales and marketing goals, but also enables the smoothest possible shopping experience for customers.
Search merchandising best practices
In virtually any form, searchandising can deliver major advantages to retailers. But to get the very most out of the it, eCommerce companies should consider best practices like the following.
Start with a Strong Foundation
Effective search merchandising begins with search results generated by a well-tuned search engine. When the search engine accurately interprets shopper queries and delivers relevant results, merchandising efforts can focus on enhancing rather than correcting those results. By starting with a strong foundation of precise, reliable search results, businesses can use merchandising techniques—like product promotions, banners, and custom ordering—to add value, spotlight key items, and create a cohesive shopping journey that truly resonates with shoppers.
Combine Automation with Merchandiser Control
Combining machine learning and AI with merchandiser’s insights enables search merchandising to achieve scalable, impactful results. AI and machine learning analyze vast amounts of data quickly, identifying patterns and optimizing search results at scale, while merchandiser control enables alignment with brand values and evolving trends. This approach allows retailers to manage large product assortments effectively, balancing efficiency and personalization to create search experiences that feel both relevant and thoughtfully curated at scale.
Perform A/B testing
A/B testing is essential in search merchandising because it allows retailers to understand what truly resonates with their shoppers. By comparing different versions of merchandising strategies—such as product placements, banners, or promotions—businesses can identify which approach drives the most engagement, conversions, or satisfaction. This data-driven approach enables continuous optimization, ensuring that merchandising decisions are informed by real shopper preferences, which ultimately leads to a more effective, responsive search experience that aligns with evolving shopper behavior and business needs.
Implement no-code search merchandising
To get the most out of search merchandising, businesses shouldn’t have to devote the time and expertise of their software developers. Instead, they should adopt no-code and low-code solutions, like FindTuner, that allow business teams to configure the criteria that shape search results.
With this approach, anyone involved in eCommerce – merchandisers, product managers, search managers and beyond – can configure search without having to learn special technical skills or tools. In addition, no-code or low-code search merchandising helps ensure that retailers can update search strategies quickly. They don’t need to begin preparing months in advance to update their search engine’s configuration so that they’re ready for a holiday sale, for example. They can also react quickly to changing market or inventory conditions by factoring them into search results.
Getting started with search merchandising
Because search merchandising involves multiple techniques and complex technology, it might seem challenging to begin benefitting from the practice at your business. But when you choose a solution like FindTuner, that’s not the case.
FindTuner’s search merchandising capabilities enable anyone to define the criteria that power personalized search. Whether you want to promote important products, tailor the search experience to different types of customers, target certain shopper attributes or all of the above, FindTuner’s low-code/no-code approach makes it easy to do so.
Large language models (LLMs) often feel like having the world’s greatest toolkit for fixing a problem you can’t quite identify. This gap can feel particularly acute when working with search indexes such as Elasticsearch, Solr, or OpenSearch. Existing search technologies are exceptional at making rapid textual matches but are unable to match documents without direct text matches.
Consider the Humble Search Bar
Finding the best search results often means going beyond what users put into the search bar. When considering a search bar, it becomes clear it inherits context. In other words, a search bar on a web site for purchasing auto parts should seek ways to apply an auto parts perspective to whatever the user enters. You shouldn’t expect the user to input something like “I’m searching for an auto part called a bumper.” Moreover, people often don’t have quite the right word to describe what they are looking for. Sometimes, they may have the right word, just not the word matching key results that would best serve them.
Large Language Models (LLMs) can bring the power of contextual inference into the search bar. A simple way to leverage that power is to use it for identifying and surfacing potential synonyms. This blog will discuss one simple approach for managing this process, considering limitations in how LLMs function as well as the volume of queries and potential synonyms that need to be considered. Human oversight will be considered a critical component necessary to avoid irrelevant or counterproductive synonyms. Due to this necessity, an overarching goal is to make human interaction as efficient and effective as possible.
A Quick Primer on LLMs
By using context inference, LLMs can make associations beyond direct text matches. In the LLM data, words is represented in a sort of coordinate system with hundreds, or even thousands, of dimensions. This coordinate system effectively creates innumerable conceptual vectors. There’s no way to know what concepts are represented in the data. They could be as fundamental as “gender”, as weirdly specific as “astrophysics”, or as nebulous as “things people think about at 3pm”. This is generally processed through a mechanism known as cosine similarity. Visually, the word “signal” might be thought about like this:
In this example, the red vector (1) might represent “things related to radios”, the green vector (2) might represent “cars”, and the blue vector (3) could be “astrophysics”. The word “signal” has a relationship to “wave”, “blinker”, and “pulsar” in each of these contexts, respectively.
Finding the Right Perspective
The diagram above is a limited representation of generalized word embeddings from LLMs such as Google’s Gemini or Meta’s Llama. They are both built from massive sets of data with no particular focus. However, as a user of one of these LLMs, a search for “signal” on the aforementioned web site of an auto parts store would ideally just utilize vector 2. Similarly, for a search on scientific papers, vectors 1 and 3 might both be applicable. As a search professional, the goal is to make use of vectors best match the user’s perspective when they fill in that search box.
Is This a Problem?
It might not seem like this is a big deal. After all, there’s no car part called a “wave”. Unfortunately, it’s possible the store could sell a window cleaner called “Bright Wave” or a product description for a window flag might include the text “waving in the wind.” A search for the term “signal” could conceivably return window cleaner and sports team flags when the user most likely desires a replacement blinker. In many ways, these represent a typical synonym issue in Solr, Elastic, OpenSearch, and other BM25 based tools. Since synonyms apply universally on a field, it’s important to find that sweet spot where documents relevant to a user are returned without generating too many false positives.
Developing a LLM to Search Synonym Pipeline
Since you never know what matches an LLM might return, validating the synonyms before implementing them is critical. In a large commerce site, you might have tens of thousands of words users search on and hundreds of thousands of potential synonyms for those words. Clearly, making this task into something a single subject matter expert or search professional can manage will take some planning.
Scoring!
The simplest mechanism to reduce the potential synonyms a human needs to consider is to look at the vector search score. All LLM based searches are done with vector searches. These kinds of searches generate a score based on distance or relevancy associated with each potential synonym which is always used to determine sort order. Each vector search will return exactly the number of values requested because, technically, every document in the vector database is a “match”, just with increasingly bad relevancy.
Let’s consider a log with 250,000 historical user searches. A search team could go through this log trying to think of potential synonyms that may find suitable results in a product catalog. Assuming they are doing due diligence and averaging roughly 15 seconds on each search, that log will require about 1000-man hours to process. So, the first thing to do is limit the maximum number of potential synonyms returned for each user search to something reasonable, like 5. Now the search team doesn’t need to try to imagine possible matches, they can simply look at the 5 that came back for each query and think “yes” or “no”. Less thinking means less time, this alone could shave off a solid third of the time.
That still leave about 650-man hours, but what if 5 options are just the maximum. After all, not every word searched by a user will have 5 words that are even in the ballpark to be used as a synonym. In fact, having 5 suitable synonyms is rare. It’s far more likely that no suitable synonyms are available. Just because the LLM thinks one word is more like the user’s query than any other word doesn’t mean the closest word is even worthy of consideration. This is where applying a threshold value on scores can drastically reduce the possibilities a search team needs to consider. Even a reasonable threshold value could reduce the word/synonym pairs up for consideration down to less than 5% of the total “matches” made. Now the 650-man hours becomes a much more manageable 30-to-35-man hours. This is the kind of effort a first-time evaluation might require, but iterative cycles might just take an hour a week after common synonym pairing have been evaluated by the search team.
Reduce Potential Synonyms
Another way to improve LLM results is to exclude words that should never be used as a synonym. It doesn’t matter if the LLM thinks “wave” is a good match for “signal” if the vector database doesn’t contain the word “wave” as an option. Pruning potential synonyms could be done automatically as a function of how potential synonyms are gathered and filtered before being added to the database.
For instance, a good way to determine a pool of potential synonyms is to draw them from a description field for products. However, description fields contain a lot of terms that LLMs consider highly interchangeable. This is notoriously true for numerical indicators. Setting up a process to block numerical words (such as “one” or even the actual number 1) removes the risk of it being offered as a synonym entirely.
Custom Source Embeddings
This is a little technical, so the details won’t be discussed here, but an LLM can be used to generate a reduced set of data based on an overarching phrase or concept. If a search is very specifically for auto parts, the LLM could generate a smaller model that is tuned based on that idea. A well-constructed phrase will create a much better set of embeddings to base the searches on, which will improve score results and make the threshold filtering more effective. However, developing a good set of embeddings is a non-trivial task.
In Conclusion
LLMs can bring suggestions to the attention that may have been overlooked. However, some human intervention will be required to ensure synonyms are not added that will adversely affect user experience. The key to a useful implementation is to reduce the amount of user searches and potential synonyms a search team needs to evaluate. Instead of 250,000 searches with an undefined set of possibilities, a good system may have the team needing only to consider a few hundred legitimate pairs in a more readable format. It may be helpful to create your own synonym management application based on these principles or take advantage of an existing product such as our FindTuner application. Good luck on your own path in turning an LLM into a synonym generating machine!
We are excited to announce that FindTuner 3.8 is immediately available! The new release delivers powerful and flexible AI-driven hybrid search and synonym features that combine Solr’s precision with advanced vector search to deliver superior search results.
Today’s online shopper demands fast, relevant, and accurate search results that deliver what they are looking for in the way they express it. With AI-powered capabilities transforming how search systems interpret context and keywords, retailers and B2B sellers want to blend traditional search precision with advanced, context-driven relevance that AI promises. These trends highlight the need for flexible search tools that can adapt to different shoppers needs, helping businesses boost sales by delivering what shoppers are looking for.
The features of this release are about delivering relevance, control, and adaptability. Our hybrid search combines the best of keyword and AI search, while the synonym management features ensures that the shopper’s language is understood. Together, these features enable retailers to elevate the search experience and increase conversions.
Hybrid Search for Superior Relevance
FindTuner’s hybrid search features combine Solr’s lexical search with AI-vectorized product data, allowing online retailers to deliver highly relevant and contextually accurate search results that match shopper intent. Online retailers and B2B sellers alike can now maximize the value of their existing Solr infrastructure while enjoying the flexibility to use any vectorization model that best suits their product data.
Key capabilities of the hybrid search feature include:
Flexible AI Integration: Built with flexibility in mind, FindTuner’s hybrid search supports any AI model. This allows e-commerce teams to maximize their existing AI investments by choosing the model that best fits their product data and shopper behavior.
Unified, Context-Driven Search Results: FindTuner’s hybrid search delivers the best of both worlds by normalizing and combining scores from lexical and AI results. This approach greatly improves search relevance, providing shoppers with results that closely match their intent in both vocabulary and context.
Merchandiser Control: Merchandisers can easily control the number of hybrid search results displayed and fine-tune the scoring impact. Hybrid search works seamlessly with FindTuner AutoTune machine learning as well as its powerful, human-touch product tuning capabilities.
Unified Management of AI and Curated Synonyms
FindTuner’s new synonym management features give merchandisers powerful tools to enhance search relevancy and improve product discoverability. Merchandisers can easily manage synonym candidates generated by AI along with custom synonym lists.
Key benefits of synonym management include:
AI-Driven Synonyms: eCommerce teams can leverage their product catalog data and shopper searches to generate synonym candidates from any AI model. With just a few clicks in FindTuner, Merchandisers can easily review, approve or reject, and publish synonyms to quickly support evolving shopper behavior.
Curated Synonyms: Merchandisers can easily add synonyms that account for the vocabulary and preferences of their shoppers. FindTuner continues to deliver the precision required to handle unusual and unique use-cases.
If you are an existing client and would like to learn more about these new features, please contact your Deployment Consultant. If you are considering FindTuner, please contact us for a demo today!
There are many studies over the years that highlight shoppers using search are more inclined to convert. Studies also show a high percentage of customer churn is due to frustrating search experiences. To increase conversion rates, enhance order values and provide the experiences today’s shoppers demand, online retailers must provide exceptional search and browse experiences. Drupal Commerce and Solr offer great search technology but with the right automation and business-user tools powered by FindTuner, you can achieve significant improvements in search performance to boost revenue, increase conversions, and drive growth.
What is FindTuner
FindTuner is a search optimization and merchandising solution that empowers retailers to provide profitable, effortless product discovery experiences. It provides machine learning models that continuously learn from shopper’s behavior, purchase history and buying patterns to deliver the best results with no manual effort along with unmatched business-user tooling that makes it easy to boost products, precisely position products in the most valuable positions, or curate the perfect search experience for a marketing campaign. FindTuner enables online retailers to synchronize merchandising and marketing strategies in real time without the need to go to IT, highlight and elevate contextually relevant facets and navigation elements and provide meaningful marketing messages to raise awareness of important products, brands and offers. FindTuner provides the perfect balance of automation and human-touch to meet any business objective.
Key Features
FindTuner is a full-featured platform that excels with any B2C or B2B use-case. The system provides business-user tooling that enables easy configuration, fast strategy authoring, insightful testing, and a robust, scalable architecture. Deployment is straightforward and once configured, it can be fed your analytics and you’ll see improved results immediately while being hands off from the start. FindTuner gives you the flexibility and freedom to:
Driving uplift with machine learning and KPI’s – FindTuner’s AutoTune system continuously improves search results using machine learning with shopper behavior, buying patterns and analytics. AutoTune instantly responds to emerging trends without manual intervention and improves shopper experience with relevant, personalized, and consistent search and category listings. FindTuner also makes it easy and intuitive to blend KPI data to dynamically rank results and positively influence conversion. KPI metrics such as conversion rate, ratings and reviews, stock status, popularity, inventory and sales rank can be used to deliver the perfect mix of products.
Facet customization made easy – Creating the ideal facet and filter experience, particularly when the product catalog has hundreds if not thousands of attributes, can be an overwhelming if not impossible task for merchandisers. FindTuner AutoTune’s Dynamic Facets feature delivers the right facets and filters based on the product results for any search or navigation. Paired with AutoTune’s facet ordering machine learning model, merchandisers can automatically show the right facets in the perfect order with no manual effort. While AutoTune delivers your core navigation experience, rest assured you have the power and control to curate facets and facet values based on business objectives.
Product Promotions that Convert – Retailers and merchandisers are empowered with tools to shape the ideal consumer experience and meet business objectives by promoting products or product groups for any combination of search, navigation and/or shopper context. FindTuner’s precise product promotion features enable you to easily control the most valuable positions in your search results. Driven by machine learning, FindTuner provides recommendations features that spotlight and elevate products to enhance cross-sell and up-sell opportunities. Merchandisers are empowered to create engaging, visual navigation links to categories and brands at any level.
Powerful and flexible targeting – Merchandising efforts can be tailored towards lucrative user segments and crafted to deliver personalized shopping experiences. Merchandising actions may be based on either broad or highly refined conditions and can take into account a shopper’s search, navigation, context or any combination allowing you to easily pinpoint the right moment with campaigns that resonate and match the shopper’s intent. Creating customized collections of products of any size, displaying promotional banners and personalizing search results help you deliver experiences that convert.
FindTuner Integration with Drupal Commerce
FindTuner is integrated with Drupal Commerce via a module that works with Drupal’s Search API and its Search API Solr modules making adoption quick and painless. Our module provides the glue that brings the storefront and the FindTuner Merchandising Server together by routing queries to the Merchandising Server which communicates with Solr and applies machine learning models and merchandising strategies to the results. Installation of the module is very simple and is all that is required to enable FindTuner’s AutoTune and search merchandising features. FindTuner easily scales to any size product collection and shopper traffic. FindTuner is architected to seamlessly handle multiple storefronts with unique product catalogs.
How to Learn More
FindTuner’s extensive machine learning and human-touch features enable online retailers to easily meet objectives while working seamlessly with Drupal Commerce and Solr. If you are looking to elevate and optimize your Solr search experiences with Drupal Commerce we’d appreciate the opportunity to speak with you and provide a demo. More information can be found on the Drupal Commerce Search Merchandising page on findtuner.com. Also, please check out our expert Solr services.
It’s no secret that brand affinity — a shopper’s preference for a particular brand — can be one of the most potent drivers of purchasing decisions. For retailers, leveraging brand affinity to influence shopper behavior is paramount for success.
But how is that done? How do you determine and factor a shopper’s brand affinities into merchandising decisions? Those questions have not always had simple answers, especially for retailers offering various products from many manufacturers.
After all, shoppers don’t typically share their preferred brands voluntarily, which means it can be a challeng to determine. Once you know a potential shopper’s brand preferences, it may not be clear how to put them to use to connect shoppers as efficiently as possible with the products they want.
However, this shouldn’t discourage online retailers from leveraging brand affinity. On the contrary, online retailers can effectively consider brand preferences when configuring search, navigation, and other website features.
Let’s examine the role of brand affinity in automated merchandising for e-commerce sites.
Brand Affinity Example
To illustrate the importance of understanding brand affinity in retail, consider a shopper who frequents your site and has purchased Nike shoes. Their purchase history reveals an apparent affinity for Nike.
Now, let’s say your online store also sells apparel. When this shopper searches for tee shirts on your platform, you could strategically display Nike-branded tee shirts at the top of the product results. Doing so would likely capture their interest, increasing your chances of making a sale.
Therefore, when used alongside other data — such as the demographic cohort that a shopper belongs to and the price points associated with the shopper’s past purchases — brand affinity can play a crucial role in helping retailers connect shoppers with products they want to purchase.
With insights into brand affinity, retailers can go beyond merely highlighting similar products; they can also suggest new products that the consumer will likely find interesting.
How To Identify Brand Affinity in E-Commerce
Most shoppers don’t overtly reveal their brand preferences. Unless they use search filters to narrow down options by brand, customers rarely go out of their way to specify which manufacturers they prefer. So, it’s up to retailers to infer brand preferences by monitoring shopper behavior on their sites. Three critical types of data can help in this regard:
Product listing clicks: If shoppers repeatedly click on (or, depending on how you structure your site, hover over) product listings from the same brand to obtain more information about them, the behavior may signal a preference for that brand.
Cart history: Consistently adding a specific brand’s products to online shopping carts indicates brand affinity.
Purchasing history: If shoppers routinely purchase an item from a given brand, that’s a strong signal of affinity.
Online retailers should systematically track clicks, cart history, and purchasing records to gain insights into a shopper’s brand preferences.
Putting Brand Affinity to Use in Online Product Results
Brand affinity is associated with an individual shopper who can be labeled using a username, user ID, or any other unique identifier.
It is then weighted against other shopper data, such as demographic cohort or geographic location, to determine products likely to be of greatest interest.
Website navigation displays and product search results are customized for the shopper based on the preferences identified in the previous step.
Using brand affinity can be a simple, automated, and scalable process, given the correct data and the right tools. The results for retailers can be significant because the easier it is for shoppers to find the products they want on a website, the more likely they are to make purchases.
Leveraging Brand Affinity in Merchandising
Unlocking the brand preferences of online shoppers need not be a guessing game. By tapping into the right data sources, online retailers can get an accurate read on which brands resonate with their customer base. Armed with this valuable insight, online retailers can formulate more effective merchandising strategies that serve both their customers and their bottom line.
At Innovent, we spend a lot of time thinking about how machine learning can improve online shopping experiences by helping retailers deliver highly personalized results to their customers. But because we’re not in the retail business ourselves, we don’t get to see the impact of our FindTuner technology firsthand.
That’s why we relish the opportunity to talk to retailers who benefit from our solutions – as we recently did when I sat down with Gautier Schaffter, senior product manager at Migros Specialized Markets, to discuss how his company leverages FindTuner to improve the impact of product searches.
Keep reading for a look at our conversation, which highlights how Migros, one of the largest retailers in Switzerland, is applying machine learning to take customer personalization to the next level by delivering highly targeted and ultra-relevant results – something that conventional search algorithms just can’t do.
Tell us about Migros Specialized Markets’s core business and its overarching tech strategy as it pertains to product search.
Migros Specialized Markets (MFM AG) focuses on the non-food segments of Migros, one of the largest retail companies in Switzerland. Our core business is to provide a wide range of high-quality products to our customers at affordable prices, while also maintaining a strong commitment to sustainability and social responsibility. MFM AG is composed of five brands (Melectronics, Micasa, SportX, Do It + Garden and Bike World), each with their own brick-and-mortar as well as online stores.
In terms of our overarching tech strategy, we strive to leverage technology to enhance the overall shopping experience for our customers. This includes providing a seamless and intuitive online shopping experience through our e-commerce platforms, as well as improving the in-store experience through various digital initiatives.
As it pertains to product search, we recognize that search is a critical component of the online shopping experience. Therefore, our tech strategy in this area focuses on delivering relevant and personalized search results to our customers. We do this by leveraging various data sources and machine learning algorithms to understand customer needs and preferences, and then surface the most relevant products accordingly. Additionally, we continuously iterate on our search algorithms to improve their accuracy and relevance over time.
In which areas or categories of MFM AG’s shopping sites is it using technology from Innovent?
Our e-commerce platform uses FindTuner to improve search results, sorting relevance, and some merchandising features on our shopping sites. This approach is in line with our overarching tech strategy to leverage technology to enhance the overall shopping experience for our customers. By using Innovent’s technology, we are able to continuously iterate on our search experience and sorting relevance to improve their accuracy over time.
Overall, our partnership with Innovent has helped us to deliver a more personalized and relevant shopping experience to our customers, which is a key priority for us.
Why was Innovent chosen and how exactly is MFM AG using Innovent technology?
We were originally looking for a partner that could help us improve our search configuration and Innovent’s experience and track record in these areas made them a natural choice. After a few rounds of optimizations, we decided to implement their FindTuner extension to push our merchandising and search optimization capabilities further.
Why did MFM AG decide to embrace machine learning? What was the driver for the decision?
MFM AG embraced machine learning as a means of enhancing the overall shopping experience for our customers. Machine learning enables us to gain a deeper understanding of customer intent and preferences.
An additional driver for our decision to embrace machine learning was the growing volume of data available to us through our e-commerce platforms. With more and more customers shopping online, we had access to a wealth of data on customer behavior and preferences that we could leverage to deliver a more relevant experience.
What benefit is machine learning adding to users’ experience? How tangible are the benefits of personalization and dynamic search optimization and what data exists to quantify those benefits?
Machine learning is adding significant benefits to our shopping experience by enabling us to deliver more personalized and relevant search results, sorting relevance, and merchandising features on our shopping sites.
One of the most important benefits of machine learning is that it allows us to better understand customer intent and preferences. By analyzing customer search queries and behavior, we can gain insights into what products customers are looking for. We then surface the most relevant products and merchandising features, which in turn drives increased engagement and conversion rates.
Another benefit of machine learning is that it allows us to continuously iterate on our search algorithms and sorting relevance to improve their accuracy and relevance over time. This means that the more customers use our platform, the better it becomes at delivering personalized and relevant search results. This leads to a virtuous cycle of increased engagement and customer satisfaction.
The benefits of personalization and dynamic search optimization can be quantified through a variety of metrics, including engagement rates, conversion rates, as well as product click-through-rate.
Similarly, what’s gained by minimizing manual tuning of the experience? What does that bring to the table?
While it is important to have human experts involved in the tuning process, leveraging machine learning algorithms and automation tools like Innovent’s FindTuner allows us to use our resources more efficiently and focus on more important or complex cases that still require human input.
By reducing the amount of manual work required for search optimization, we are able to free up our experts to focus on more complex and high-impact cases. This helps us to improve the overall shopping experience for our customers, as we are able to devote more attention to improving key areas of our platform.
Overall, the technology provided by Innovent has allowed us to optimize our search experience more efficiently, reduce the amount of manual work required, and focus on higher-impact cases that require expert attention.
How does the process work? Could you differentiate the ML process for us from something like the Amazon algorithm? Has it changed the way that the day-to-day reality of Migros Specialized Markets works?
The process of using machine learning for product search involves several key steps. First, we collect anonymized behavior data including search queries and click data as well as product performance. This data is then used to train machine learning algorithms to understand customer intent and surface the most relevant products accordingly.
In terms of day-to-day reality, using machine learning for product search has certainly changed the way that we work at MFM AG. It has allowed us to provide a more personalized and relevant shopping experience for our customers, which is a key priority for us. However, it’s important to note that while machine learning has enabled us to improve the search experience, it is not a silver bullet solution. There is still a lot of work required to ensure that our models are properly trained, and we continue to rely on human experts to fine-tune the search experience and provide oversight to ensure that the results are accurate and relevant.
Overall, machine learning has been a valuable tool for enhancing the search experience at Migros Specialized Markets, but it is just one piece of a larger puzzle that includes human expertise, data collection, and ongoing iteration and optimization.
Talk to us about the potential of scalable merchandising in large catalogs. How are you leveraging that benefit? How does it enhance the customer experience?
Using scalable merchandising solutions allows data-based product recommendations, which can help improve the overall customer experience. For example, by taking a customer’s purchase history and browsing behavior into account, it is possible to suggest products that are likely to interest the customer, leading to increased customer satisfaction and loyalty.
Additionally, scalable merchandising helps manage the inventory more effectively by highlighting products that are selling well and predicting which products are likely to sell out.
Do you think machine learning and intensive personalization of the shopping experience are the wave of the future?
Definitely. Studies have shown that more and more users expect personalized experiences and relevant content. This allows customers to shop more efficiently and discover relevant products based on their preferences and behavior. Machine learning is the most effective way to effectively and efficiently leverage data to offer such experiences.
Would you like to share anything else that you feel is useful to give business readers insight into integrating ML into their business models?
Sure. Here are some key pointers based on our experience so far:
Start small: Don’t try to implement machine learning across your entire business all at once. Start with a small project and build from there. This will help you to identify any issues or obstacles early on, and make it easier to scale up in the future.
Focus on the customer: Machine learning is a tool to help you provide better customer experiences. Keep the customer at the center of your ML initiatives and focus on providing them with more personalized and relevant experiences.
Get the right talent: Machine learning requires specialized skills, so it’s important to have the right talent on your team. Consider hiring data scientists, machine learning engineers, and other experts who can help you build and implement ML models.
Invest in data quality: Machine learning models are only as good as the data they’re trained on. Make sure you have high-quality data that is relevant and up-to-date.
Monitor and refine: Machine learning models are not set-and-forget solutions. You need to monitor their performance and refine them over time to ensure they continue to deliver value.
Conclusion
As Gautier’s experience highlights, truly standing out in the highly competitive world of online retail requires more than just standard product searches. Forward-thinking businesses need to take advantage of next-generation technologies that significantly enhance search tools’ ability to surface products that individual shoppers will find relevant and compelling.
At Innovent, we’re proud to be delivering those solutions to Migros and retailers like it across the globe.
Online shopping and digital marketing concept, Woman using digital laptop with shopping cart icon on screen on dark background
Most online retailers recognize the importance of artificial intelligence and machine learning technologies. In fact, more than four-fifths of e-commerce businesses report that they’re either exploring or already using AI solutions to increase business success.
Whether these companies use AI to maximum effect, however, depends on exactly how they integrate AI into their operations. Leveraging AI to address basic needs through techniques like simple clickstream analytics isn’t enough on its own to maximize conversion rates and revenue.
That’s why retailers that want to take full advantage of AI should be thinking beyond simple AI use cases in e-commerce. Those use cases are one step toward success, but they’re not the full story.
Allow me to explain by discussing common use cases for AI in e-commerce and differentiating basic from more advanced ones.
AI in Retail: Simple Examples
Let’s start with relatively simple examples of how online retailers can use AI — or something approaching AI — to enhance their business.
One of the simplest use cases to consider in this regard is clickstream analytics. Clickstream analytics allows retailers to track user activity on their websites — e.g., which items users click on most frequently and which pages they navigate through on their way to making a purchase. By employing algorithms to analyze this data in the aggregate, retailers can establish a baseline of customer behavior. They can also identify opportunities to increase customer satisfaction and conversion by, for example, placing items that customers click on more frequently at the top of search results.
Insights like these are good. However, for many e-commerce businesses they’re not enough to achieve true sales optimization. Data points like which products site visitors click on most often aren’t sufficient on their own to solve questions like which products will drive the highest revenue, because these limited data points don’t take into account factors such as whether items are actually in inventory or what the margin is on the items. They’re just a blunt — and relatively imprecise — measure of which products are most likely to draw clicks.
A slightly more complex, but still basic, example of how e-commerce businesses can use AI is customizing facets within website navigation. Facets help site visitors filter products that appear within search results based on factors like product color or size. Using AI, businesses can identify which facets are most popular among customers and prioritize them within navigation menus.
AI-driven facet customization is a useful way to help optimize the customer experience and, in turn, increase conversion rates. But here again, this is a basic use case for AI that leads to limited value. The signals that drive facet customization are restricted to data points like how often visitors use different facets, which optimizes only one specific part of the customer journey — and which does it based on generic, one-dimensional data.
Advanced Uses for AI in Retail
What can e-commerce businesses do to take AI to the next level? The answer involves two key pillars.
The first is collecting a multitude of data points that help businesses understand customer needs and align them with business priorities in a holistic way. This data might include basic information, like the kind that drives clickstream analytics, but it should also include data like product ratings and reviews, product inventory status, product shipping time, and perhaps even data points that reflect how close the retailer’s relationship is to different product vendors.
The second essential ingredient in advanced AI for retail is algorithms that can dynamically rank search results using the multifaceted data described above. Dynamic ranking is essential not just because it ensures that rankings can constantly evolve along with continuously changing data, but also that search results can be truly customized and personalized for each customer. In turn, businesses are able to achieve higher conversion rates than they would through a blunter approach wherein product search results, displays and navigation are optimized for customers in general, not personalized for individuals.
Of course, it’s important while using AI-powered optimizations to give merchandisers control over the product search results delivered by sophisticated AI. For example, if your business wants to prioritize one vendor’s products, that policy should inform search results to ensure the products rank highly — even if other data would suggest that they should receive less priority.
This is the approach that e-commerce businesses at the forefront of the AI revolution are using to get the very most out of AI and ML as solutions for optimizing online shopping and maximizing revenue. They also take advantage of more basic AI-based techniques, like clickstream analytics, but they realize that those strategies are only the tip of the iceberg when it comes to AI in retail.
Conclusion
Going forward, adopting basic AI will no longer be enough to ensure e-commerce business success. In a world where most retailers are already using some type of AI, companies seeking to lead need to adopt advanced AI-based techniques that allow them to leverage all data at their disposal to create the most engaging, dynamic and personalized shopping experience possible, while also aligning that experience with business priorities.
Manage Cookie Consent
To provide the best experiences, we use technologies like cookies to store and/or access device information. Consenting to these technologies will allow us to process data such as browsing behavior or unique IDs on this site. Not consenting or withdrawing consent, may adversely affect certain features and functions.
Functional
Always active
The technical storage or access is strictly necessary for the legitimate purpose of enabling the use of a specific service explicitly requested by the subscriber or user, or for the sole purpose of carrying out the transmission of a communication over an electronic communications network.
Preferences
The technical storage or access is necessary for the legitimate purpose of storing preferences that are not requested by the subscriber or user.
Statistics
The technical storage or access that is used exclusively for statistical purposes.The technical storage or access that is used exclusively for anonymous statistical purposes. Without a subpoena, voluntary compliance on the part of your Internet Service Provider, or additional records from a third party, information stored or retrieved for this purpose alone cannot usually be used to identify you.
Marketing
The technical storage or access is required to create user profiles to send advertising, or to track the user on a website or across several websites for similar marketing purposes.
