Automated Product Matching Pipeline
Fashion Retail Client · Digital Shelf Analytics
The same sneaker has a different title, a different photo, and a different SKU on every retailer's site. Comparing prices across them starts with solving that mismatch.
Digital shelf analytics sounds simple until you try to compare "the same product" across two retailers and realize there's no shared ID connecting them. One site calls it "Men's Classic Leather Sneaker - White," another calls it "White Leather Trainers, Men"; the photos are shot differently, and the size and color attributes are structured differently too.
The Build
A price comparison built on a title mismatch isn't comparing the same product at all. The matching layer is the unglamorous, load-bearing piece underneath every other kind of retail intelligence: pricing, assortment gaps and competitor benchmarking are all only as trustworthy as the matching beneath them.
A 3,300-SKU master list from a fashion retail client, matched against listings across 9 Indian e-commerce platforms: inconsistent titles, differently shot images, and differently structured size and color attributes on every site.
A pipeline that reconciles listings across competing fashion retailers despite inconsistent titles, images, and attributes, turning approximate comparisons into genuinely apples-to-apples ones.
Tech: Python · Playwright · BeautifulSoup · Groq API · ScraperAPI · Google Sheets API
A false match silently corrupts everything built on top of it. A missed match is just a gap.
That asymmetry shaped nearly every decision in the matching logic. It's tempting to tune a matcher for the highest overall accuracy, but the cost of a false positive and a false negative aren't the same, so the system deliberately errs toward caution: when it isn't confident two listings are the same product, it says so, rather than guessing. Optimizing for accuracy on paper isn't the same as optimizing for the outcomes that actually matter downstream.
Matching 3,300 SKUs across 9 Indian e-commerce platforms:
Match Rate by Platform
Live Monitoring: Status Distribution
AJIO: Improvement After Secondary Search
Impact: 87% of the catalog matched automatically, cutting manual reconciliation effort by roughly 68% and turning approximate cross-retailer comparisons into ones a pricing or assortment team can actually trust.
Working through a product matching problem?
Happy to talk through matching strategy, attribute extraction, or where precision and recall trade off against each other.