The Split/Test Digest

How Return Customers Can Drive Order Spikes in Ecommerce | Constructor

anastasiia.iakunina@constructor.io (Anastasia Yakunina) — Thu, 05 Mar 2026 19:34:09 GMT

At Constructor, we access petabytes of data across a variety of both B2C and B2B verticals. Given the massive gifting events that just occurred over the past few months (namely Black Friday, Christmas, and Valentine’s Day) and occasions like Mother’s Day and graduations just around the corner, we thought it’d be interesting to analyze data from a traditionally gift-reliant industry — jewelry — to see how shopping behavior changes over the course of a year.

Black Friday 2025: What We Learned About Shopper Behavior and Product Discovery

Nate Roy — Tue, 09 Dec 2025 17:14:45 GMT

This post was written in collaboration with Vardan Aslanyan, Product Director at Constructor, and Anastasia Yakunina, Data Storyteller at Constructor.

Black Friday 2025 was the largest discovery day ever on Constructor’s platform, with 2.27 billion total discovery requests across search, autosuggest, browse, and recommendations.

See How 40M Lipstick Searches Expose Need for Behavior-Driven Discovery | Constructor

anastasiia.iakunina@constructor.io (Anastasia Yakunina) — Fri, 14 Nov 2025 16:21:31 GMT

For ecommerce teams, the search bar is high-stakes real estate. It is often the first and most critical touchpoint for a shopper on a retailer’s website, and shoppers who use search convert at a rate 2.5X higher compared to shoppers who browse. Yet despite its importance, most retail search experiences fall short. Shoppers in every category — from apparel to electronics, beauty, and more — often use broad, familiar terms that don’t adequately describe their true intent, making it challenging for traditional keyword-based search engines to deliver satisfactory results.

Matching Intent to Attractiveness for Home Goods | Constructor

Nate Roy — Thu, 30 Oct 2025 00:26:52 GMT

Sixty-six percent of home goods shoppers include ecommerce in their buying journey — whether it’s simply to start their research and pre-shop before visiting a store, find showroom pieces online, or take an entirely digital path. But while shoppers have evolved, most ecommerce search engines haven’t. They still rely on rigid keyword matching to interpret nuanced, emotional, or style-driven keywords – leaving many high-intent shoppers unseen.

Unlocking Regional Conversion Gains with Geo-Personalized Ranking | Constructor

Nate Roy — Fri, 10 Oct 2025 15:00:00 GMT

Retailers operating in multiple regions often default to one ranking algorithm for all markets. The upside is obvious: more data to train on, simpler infrastructure, and consistent experiences across geographies.

Optimizing Search Result Page Experiences: 4 Strategies to A/B Test

Nate Roy — Mon, 29 Sep 2025 10:43:23 GMT

After a site searcher submits their query, what appears next can make or break their journey. Should you show traditional search results? Redirect exact matches to their corresponding category pages? What should you show if no matches are found?

What 10 Million Jeans Purchases Reveal About Personalization

anastasiia.iakunina@constructor.io (Anastasia Yakunina) — Tue, 26 Aug 2025 15:05:12 GMT

Retailers often balance personalization with trends and competitor benchmarks, but we wondered how much outside signals really reflect the reality of a retailer’s own audience. What if the patterns hiding in clickstream data told a different story altogether?

5 Autocomplete Optimizations Uncovered Through A/B Testing

Nate Roy — Wed, 30 Jul 2025 15:41:14 GMT

We have the data: across our customer base, 1 in every 4 online visitors use site search within their sessions, and the 24% of users that search drive 44% of revenue, on average. Optimizing the site search experience can push that metric even higher on an individual website.

Still Running Classic A/B Tests? Here’s Why That Might Be a Big Mistake

Polina Egubova — Tue, 27 May 2025 13:00:00 GMT

Imagine this. You’re running an A/B test. You’ve followed every best practice: scoped the hypothesis, implemented the feature cleanly, launched to 50% of users, and hit your minimum sample size. You check your metrics: revenue is up, conversion is climbing, and bounce rate is stable.

Adapting Ranking Models to Short-Term Sales Behavior

Nate Roy — Mon, 28 Apr 2025 10:20:14 GMT

This post was written in collaboration with Valery Bezrukova, VP Product at Constructor.