Glossary · E-commerce ML
Real-Time Personalization
also: session-based recommendation · in-session personalization
Definition
Real-time personalization adapts product recommendations, content, and pricing within a session based on immediate behavior signals — dwell time, scroll depth, added items, search queries. Contextual-bandit systems with streaming feature stores enable policy updates in milliseconds, producing 10–25% lift over batch-trained models.
Traditional recommenders train nightly on batched user-item interactions. Real-time personalization closes the loop: session-level signals update features in a feature store, which feeds a bandit or online-learning model that selects the next action within milliseconds. The architecture requires low-latency feature serving (Redis, Feast), an online policy (contextual bandit, reinforcement learning), and logged-experience training that handles selection bias. Gains compound with session depth — later-session decisions benefit more.
Essays on this concept
- E-commerce ML
Cold-Start Problem Solved: Few-Shot Learning for New Product Recommendations Using Meta-Learning
New products get no recommendations. No recommendations means no clicks. No clicks means no data. No data means no recommendations. Meta-learning breaks this loop by transferring knowledge from products that came before.
- E-commerce ML
Dynamic Pricing Under Demand Uncertainty: A Contextual Bandit Approach with Fairness Constraints
Airlines have done dynamic pricing for decades. E-commerce is catching up — but without the fairness constraints that prevent algorithms from charging different people different prices for the same product based on inferred willingness to pay.
- E-commerce ML
Graph Neural Networks for Cross-Sell: Modeling the Product Co-Purchase Network at Scale
Association rules find that beer and diapers are co-purchased. Graph neural networks understand why — the underlying structure of complementary needs, occasion-based shopping, and brand affinity networks that connect products across categories.
- E-commerce ML
Real-Time Fraud Detection at Checkout: A Streaming ML Pipeline Architecture with Sub-100ms Latency
You have 100 milliseconds to decide whether a transaction is fraudulent. In that window, you need to compute 200+ features from streaming data, run inference on a model trained on 1:1000 class imbalance, and return a score that balances revenue loss against customer friction.
- Marketing Engineering
Building a Real-Time Personalization Engine: From Contextual Bandits to Deep Reinforcement Learning
A/B tests answer 'which variant is best on average.' Contextual bandits answer 'which variant is best for this user right now.' The difference in cumulative regret — and revenue — compounds daily.
- E-commerce ML
Transformer-Based Product Embeddings: Outperforming Collaborative Filtering with Multimodal Representations
Collaborative filtering needs a user to buy before it can recommend. Transformer-based embeddings understand products from their descriptions, images, and the behavioral context of browsing sessions — no purchase history required.
Related concepts