Recommender system
A recommender system is software that predicts, selects, or ranks items, content, or actions for users based on available information about users, items, or context.
Grokking Machine Learning
A recommendation system is a software system that suggests items, content, or actions to users based on available information about them or their context.
- How it is used
- Uses predictions about user interest or actions to suggest videos, music, products, or apps.
- How deep it goes
- Works from features and labels through decision-tree split selection, comparing candidate splits with accuracy, Gini impurity, or entropy.
- Examples
- Uses video, music, and product predictions alongside an app dataset with user ages, platforms, and downloads.
- What you can do after
- Build an app recommender by choosing useful features and recursively splitting users with a decision tree.
Read how Grokking Machine Learning explains recommender system →
The Art of AI Product Development
A recommendation system is a computational system that generates personalized suggestions by estimating which items or content may interest a user.
- How it is used
- Uses personalized suggestions to support discovery, engagement, retention, and sales in streaming and shopping products.
- How deep it goes
- Explains filtering approaches and ongoing evaluation through examples, without detailing model implementation.
- Examples
- Uses music discovery, complementary fashion purchases, black boots, and comparisons of user-based and item-based filtering.
- What you can do after
- Practice/perform approach selection and iterative evaluation using click-through rate, conversion rate, A/B tests, and user feedback.
Read how The Art of AI Product Development explains recommender system →
AI-Powered Search
A software system that infers user interests or behaviors and delivers content or items that it predicts will match them, without requiring an explicit query for each result.
- How it is used
- Positions recommender systems as AI-powered information-retrieval systems for delivering relevant content from inferred user interests.
- How deep it goes
- Classifies content-based, behavior-based, and multimodal approaches but stops short of algorithm internals or implementation procedures.
- Examples
- Uses e-commerce related-item lists based on browsing, purchasing, and interest in similar items.
- What you can do after
- Evaluate recommendation designs by comparing available content signals, behavioral interactions, and user control.
Machine Learning Platform Engineering
A recommendation system is a software system that predicts or ranks items, content, or actions for users or other entities.
- How it is used
- Deploys ranked movie recommendations through a reproducible ML pipeline spanning data preparation, training, validation, and monitoring.
- How deep it goes
- Builds the surrounding infrastructure and drift workflow, while deliberately deferring detailed recommendation-algorithm exploration.
- Examples
- Uses MovieLens ratings, Parquet datasets, user and item factors, modified ratings, and deepchecks FeatureDrift comparisons.
- What you can do after
- Build it from scratch as a production-oriented movie recommendation pipeline with tracked experiments and monitored latent-factor drift.
Read how Machine Learning Platform Engineering explains recommender system →
Graph Algorithms for Data Science
A recommendation system generates ranked or selected items for users based on user, item, or interaction information.
- How it is used
- Improves channel recommendations by combining established audience overlap with predicted future overlap.
- How deep it goes
- Explains the workflow through link prediction metrics and classification-model training, without detailing model implementation.
- Examples
- Uses Twitch channel recommendations and relates the approach to movies, products, and medical concepts.
- What you can do after
- Evaluate recommendation improvements by combining existing relationships with predicted future relationships.
Read how Graph Algorithms for Data Science explains recommender system →
Financial AI in Practice
A software system that generates recommendations from data or predictive models.
- How it is used
- Surfaces relevant assets, news, and peer activity to support investment discovery rather than direct sales.
- How deep it goes
- Connects user context to fast-moving content and describes semantic cold-start matching, without detailing ranking internals.
- Examples
- Uses an Alpha News feed, asset and news discovery, and peer activity such as users watching NVDA also watching AMD.
- What you can do after
- Evaluate recommendations by relevance, retention, and dwell time rather than conversion alone, while preserving platform neutrality.
Read how Financial AI in Practice explains recommender system →
First-Party Data Activation
A software system that predicts and presents items, content, or actions likely to be relevant to an individual.
- How it is used
- Translates customer insights into personalized experiences and engagement across multiple channels.
- How deep it goes
- Explains filtering approaches, privacy practices, transparency, and consent, but not implementation mechanics.
- Examples
- Uses personalized suggestions, contextual targeting, multi-channel campaigns, and differential privacy in A/B testing.
- What you can do after
- Apply it via collaborative or content-based filtering to deliver relevant suggestions while limiting unnecessary personal-data collection.
Read how First-Party Data Activation explains recommender system →
Causal Inference for Data Science
A recommender system is a software system that suggests items or actions to users based on available information about them and the items.
- How it is used
- Frames recommender systems as interventions whose behavioral effect should be separated from their predictive accuracy.
- How deep it goes
- Contrasts prediction with causation, introduces causal graphs, and motivates A/B testing without detailing recommender implementation.
- Examples
- Uses streaming recommendations, e-commerce suggestions, autocomplete, supermarket bread purchases, and a mobile-app A/B test.
- What you can do after
- Evaluate recommendation impact via an A/B test rather than relying only on predictive accuracy.
Read how Causal Inference for Data Science explains recommender system →
Related concepts
- recommendationproduces · A recommendation is a suggested item, choice, or course of action, based on available information, intended to guide a decision.
- language modelused by · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
- candidate sourcinghas part · Candidate sourcing is the process of identifying potentially suitable candidates from a larger pool for further consideration.
- similarity metricuses · A similarity measure is a rule that quantifies or characterizes how alike two objects or representations are according to selected properties.
- collaborative filteringincludes · Collaborative filtering is a recommendation technique that infers preferences or associations from interaction patterns among users, items, or other entities.
- decision treeused by · A decision tree is a branching structure that represents sequential tests or choices, with paths leading to outcomes, predictions, or actions.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.