Recommendation systems

Recommendation systems reading path

A focused path through collaborative filtering, cold-start, quality metrics, ranking, richer signals, and AI-mediated product discovery.

ALS Collaborative Filtering for Implicit Feedback Recommendations
Start here
ALS Collaborative Filtering for Implicit Feedback Recommendations

A technical walkthrough of Alternating Least Squares, weighted ALS, and the Hu-Koren-Volinsky implicit feedback framework behind production recommendations.

Read the foundation →
The Cold-Start Problem in Recommendation Systems (and What to Do About It)
Engineering
The Cold-Start Problem in Recommendation Systems (and What to Do About It)

Every recommendation system has a cold-start problem. This post explains practical production strategies for user and item cold-start paths.

How to Know If Your Recommendations Are Working: NDCG, Hit Rate, and Coverage
Engineering
How to Know If Your Recommendations Are Working: NDCG, Hit Rate, and Coverage

Most teams track CTR and call it done. Here's what NDCG, hit rate, and catalogue coverage actually measure — and how to use them before you ship.

How We Measure Recommendation Quality — And Why We're Open-Sourcing It
Engineering
How We Measure Recommendation Quality — And Why We're Open-Sourcing It

Most recommendation vendors give you a black box. We built an open evaluation harness so you can score any system — including ours — with your own data.

Why Recommendation Quality Now Depends on Richer Signals Than Clicks Alone
Industry Analysis
Why Recommendation Quality Now Depends on Richer Signals Than Clicks Alone

Recent updates from Meta, Google, retail media infrastructure providers, and agentic commerce platforms point to the same lesson: recommendation quality increasingly depends on richer feedback, stronger metadata, and production-grade retrieval rather than clicks alone.

App Recommendation Engines: Why They Are Core to Modern Apps
Product Strategy
App Recommendation Engines: Why They Are Core to Modern Apps

A practical look at how app recommendation engines power user engagement, discovery, retention, and personalised experiences.

The Case Against Over-Optimising Recommendation Engines
Product Strategy
The Case Against Over-Optimising Recommendation Engines

Why overly precise recommendation models can harm user satisfaction and what to do instead.

AI Shopping Assistants, Brand Discovery, and Product Discovery
Product Strategy
AI Shopping Assistants, Brand Discovery, and Product Discovery

AI shopping assistants are becoming a brand discovery layer for ecommerce. That changes where relevance gets decided, who controls product discovery, and how recommendation systems need to adapt.

Announcing NSL's Next-Generation Retrieval and Ranking Stack
Product Launch
Announcing NSL's Next-Generation Retrieval and Ranking Stack

NeuronSearchLab now supports a broader retrieval and ranking stack: content embeddings, two-tower retrieval, gSASRec-style sequential retrieval, Semantic-ID generative retrieval, XGBoost rankers, MMoE, PLE, and bounded reranking.