The Inspired by Your Browsing History algorithm refines recommendations by mining a shopper’s past interactions—both within the current session and across previous visits. By blending session-based signals with content-based analysis of viewed items, IBYBH delivers highly personalized suggestions that resonate with each user’s unique interests.
Session-Based Modeling
Examines the sequence of pages visited, dwell times, and in-session interactions to surface products aligned with the user’s immediate browsing context.
Content-Based Analysis
Analyzes attributes (e.g., category, brand, features) of items the user engaged with, building a profile of their long-term preferences.
Hybrid Scoring
Combines session and content signals into a unified relevance score, ranking products that best match both recent and historical behaviors.
A shopper browses several bohemian dresses across multiple sessions.
IBYBH analyzes both their recent clicks and overall browsing patterns.
On the Homepage, the widget surfaces new boho-style dresses and complementary accessories.
On a Product Page, it highlights the exact dress previously viewed plus similar items in matching colors or prints.
By weaving together session context and content attributes, IBYBH keeps recommendations fresh, relevant, and deeply personalized—turning every visit into a bespoke shopping journey.