There’s been plenty of confusion and misinformation in the market around ecommerce search. Vendors make bold claims about which search technologies are on the way out and which ones are “innovative,” but these claims are often misleading or outright false. A lot of technical jargon also gets thrown around, leading to confusion about what’s current and what’s not.
Ultimately, customers are just looking for ways to drive real outcomes — revenue per visitor and conversion — and ensure that they’re future-proofing their search investments. That’s why I’m here to dispel some myths around ecommerce search and share insights into where I believe the future of search is headed.
Claim 1: Simply Having AI in Your Search Is Enough
Many vendors tout the latest AI technologies as their claim on why they are more modern than others. However, with how quickly AI has evolved, not all AI is built the same — search solutions created without next-generation AI simply can’t keep up with modern expectations.
At Bloomreach, we have upgraded the Discovery core with GenAI including models from Google, OpenAI, and NVIDIA, which allows us to serve any queries — from very precise searches to natural language searches — and deliver unprecedented relevance.
Plus, we’re constantly fine-tuning our AI with the latest advancements. If you’re talking to a vendor who hasn’t updated their search core in the last few months (or even weeks), they’re already way behind. Without advanced AI built into the very foundation of their products, you’ll need nothing short of a complete rearchitecture to keep customers coming back.
Of course, the proof is in the numbers. We’d be more than happy to put our search solutions to the test and prove to you that our technology is the best in the market.
Claim 2: Clickstream-Based Machine Learning Is a New Innovation
Clickstream-based machine learning (ML) analyzes a user’s on-site behavior to personalize their search experience. We’ve heard some recent claims about this being a new or pioneering innovation. Honestly, of all the claims we’ve heard floating around, this one is by far the most egregious and ridiculous.
Is the technology effective? Absolutely. Is it new? Absolutely not.
It’s funny — we must have missed the memo of others being pioneers of this technology when we literally patented* it years ago (starting in 2012)! See the footnote below for a list of relevant patents. Certainly not a leapfrog of innovation, but glad to hear others are playing catch-up!
Bloomreach Discovery uses clickstream data (among many other data sources) and has long enabled features like personalized search results and tailored product rankings based on user behavior.
Claim 3: The Future Is Transformer-Powered Product Discovery
Finally, you’ll hear vendors tout transformers as the future of product discovery. If that’s the case, then I guess we’ve been living in the future, as we’ve been utilizing transformers in Bloomreach Discovery since 2022!
Built on proprietary technology, our search can discern nuanced differences like “milk chocolate” versus “chocolate milk” or “dress shirt” versus “shirt dress.” We augment this with transformers, including BERT (bi-directional encoder representations from transformers) for natural language processing and ViT and DETR for visual search capabilities.
BERT analyzes words in context, enabling our search to grasp nuances, idiomatic expressions, and subtleties across languages. Fine-tuned with over 15 years of commerce-specific semantic data, our solution excels in delivering precise, context-aware results tailored for ecommerce across a wide range of languages.
We also can’t forget that large language models (LLMs) are transformer models. Bloomreach Discovery leverages LLMs in search recall to ensure all potential candidates are considered during recall generation, as well as for search optimization to refine the final result set. LLMs of course can be applied in myriad areas to improve both search ranking and relevance, and we continue to build on our innovation in this area. We would love to share our roadmap with you — just give us a holler!
The Future of Search
Let’s move beyond falsehoods and focus on what truly lies ahead for ecommerce search:
Search Will Become More Conversational
Shoppers will increasingly demand natural, personalized experiences. Conversational shopping agents like Bloomreach Clarity will revolutionize ecommerce by scaling the personal touch of in-store sales associates to the digital realm.
We’ve already seen some incredible results from our customers with Bloomreach Clarity, including a 35.2% increase in conversion rate, a 39.8% increase in revenue per visit, and a 28.1% lower exit rate.
With that kind of performance, you have to wonder if the search bar itself may end up being a thing of the past!
The Focus Will Be on People, Not Products
As AI continues to advance, merchandisers will no longer be expected to optimize for products, but for people. This means that features like clickstream personalization will soon be commoditized.
Instead, as search becomes more conversational, you’ll get to truly and deeply understand each customer beyond what they clicked on when they visited your website the other day. You’ll know their interests, where they’ve spent time with you, what they’ve purchased (and returned), what preferences they’ve expressed in their conversations with you, and so on.
To activate all of this data, you’ll need a zero-party and first-party customer data engine that can power personalized search experiences. And then, you need to think beyond search to provide the same personalized experience across any touchpoint — email, SMS, website, in-store, mobile app, etc. You can do that today with Bloomreach!
Customers Will Want More Control Over AI
Product Managers will gain direct control over AI algorithms, enabling hyper-tailored search experiences. At Bloomreach, this vision is embodied in AI Studio, which allows teams to deploy advanced algorithms or customize them entirely without additional overhead.
We still provide an advanced out-of-the-box learn-to-rank (LTR) algorithm that teams can deploy with a single click, but we’ve also added options for even more control.
Product teams can now specify their own signals to add to the LTR algorithm or they can even completely customize the algorithm. This gives enterprise teams a way to develop specialized and custom models without having to spend the resources building complex and scalable search infrastructure on their own.
Don’t Fall for Falsehoods — Future-Proof Your Success With Bloomreach
The next time you hear claims dismissing a technology or hear a bunch of technical jargon, just look at the transformative results our Discovery customers have achieved. When vendors boast about clickstream personalization, check our patents. And when they hype transformers as groundbreaking, know we’ve been using this technology at Bloomreach for years now.
True innovation isn’t about technology choices — it’s about pushing boundaries, envisioning what’s next, and delivering the business outcomes that matter most to you. Choose a partner like Bloomreach to future-proof your success and stay ahead in ecommerce search.
*US Patent 9,384,244, US Patent 9,830,392, US Patent 10,394,894, US Patent 10,497,042, and US Patent 10,810,275
