Redesigning Earrings Discovery for a Large-Scale Catalog
Redesigning the taxonomy for Emily Carr University's creative thesis collection drove a 27% increase in task completion rate across tested user flows.
The Challenge
Amazon.in's earrings catalog held 140,000 products. Most were invisible to the shoppers they were built for. Discovery was limited to rigid attribute filters such as gender, type, colour, metal. Over 100,000 products were incorrectly tagged. Browsing surfaces only amplified what was already popular, leaving emerging styles buried. A dedicated storefront was a rare window to rebuild how users find earrings entirely.
How do you make 140,000 earring products discoverable to a shopper who knows exactly what she wants to feel, but has no idea how to find it?
Company
Amazon India
Timeline
2018
—
2019
Role
UX & Product Designer
Work
Research · Information Architecture · ML Collaboration · Store Merchandising · Cross-functional Delivery
The catalog was not small.
The structure was.
62.5% of Indian jewellery customers buy earrings,
making it the largest subcategory in a 540,000-product catalog.
The filters available? Gender. Type. Colour. Metal. Not one for occasion. Not one for style. Not one for face type. That is not how anyone has ever thought about buying earrings.
Underneath that was a harder problem.
Over 100,000 products were incorrectly tagged - pearl earrings appearing under gold jewellery, fashion pieces buried inside traditional categories. Browsing surfaces highlighted only what was already popular, leaving emerging styles completely invisible. The catalog was not just badly structured. It was actively misleading the people trying to use it.
62.5% of Indian jewellery customers buy earrings - making it the dominant category by far.
90% of earring shoppers browse. None of the navigation was built for them.
100 participants. A quantitative survey and behavioral analysis surfaced the gap the system had never acknowledged.
Users came to the platform with intent - a wedding, a first date, a mood. The platform asked them to navigate taxonomy.
That translation was the first point of failure.
Visual display drove 75% of purchase decisions. Yet products were shown in isolation - no styling context, no occasion framing, no help imagining real-world wear.
Decision-making depended on occasion, personal style, and identity. None of that was reflected anywhere in the system.
It Was Not Just Amazon
100 participants. A quantitative survey and behavioral analysis surfaced the gap the system had never acknowledged.
Benchmarking Amazon, Flipkart, Nykaa, and Myntra revealed a category-wide failure.
Amazon led on brand filtering - useful only when a user already knows what they want. For the 90% who browse with no brand in mind, every major platform failed in exactly the same way. Occasion browsing: absent. Face type: absent. Style-led entry points: absent.
This was not a gap in one product. It was a gap in the entire category and a clear opportunity for improvement.
Core Insight
Users did not search for what earrings are. They searched for what earrings mean.
The system described earrings as objects with fixed attributes. Users experienced them as extensions of identity and occasion.
"What would I wear to a wedding?" "What suits my face?" "What feels like me right now?"
These were the real questions. The catalog answered in metal, size, and earring type. Redesigning the filters would not have fixed this. The information architecture itself had to change.
Scaling the Fix with Machine Learning
The tagging problem was too large to solve by hand. Before building a better experience, the catalog itself had to be repaired - and machine learning was the only way to do it at scale.
100,000+ products incorrectly categorized. Fashion jewelry filed as traditional. Pearl earrings listed under gold. The system's own data was working against it - and manually retagging at that scale was not feasible.
I worked with the ML team to retrain the tagging model. Initial models trained only on product descriptions produced weak accuracy scores. Text alone was not enough signal. The first attempt produced just 43% accuracy.
The fix: introduce product images into the training data. Accuracy improved to 93%. Products that fell below the confidence threshold were quarantined and flagged for manual review - ensuring nothing was auto-tagged incorrectly. In parallel, I defined 23 occasion-based taxonomy labels - giving the catalog a shared discovery language that matched how users actually search and choose.
The Design
Wireframe: The redesigned information architecture replaced flat categorical navigation with three context-first paths. Shop by Occasion aligned the catalog with real decision moments. Shop by Style reflected personal expression. Shop by Face Type answered a question users had always asked and no platform had ever directly addressed.
Scroll inside desktop to see entire wireframe.
High-Fidelity Prototype: The high-fidelity execution prioritized visual richness over information density. Rich editorial imagery, contextual curation, craft-based browsing. The goal: help users imagine wearing an earring, not just viewing one. Built for desktop and mobile with the same context-first logic throughout.
2% monthly revenue growth with 85% engagement.
An A/B test validated the approach. The launch confirmed it.
The test confirmed what research had predicted - when structure aligns with how users interpret and choose jewelry in real-world contexts, behaviour changes.
The store launched. Monthly revenue increased by 2% - significant at Amazon.in's scale. Discovery improved across 100,000+ products. The 23 occasion labels finally gave users entry points that matched how they actually shop.
Standard product listing with attribute-based filters and a popularity-driven product grid. 38% engagement across discovery surfaces.
Context-first storefront with editorial hero, Shop by Style navigation, and occasion-led discovery. 85% engagement across discovery surfaces.
