Interactive map loads when it comes into view.
Use the mouse wheel or two fingers (on touchscreens) to zoom in and out of the map.
Topic orientation
Recommender system at a glance
The strongest research directions include Approaches and Evaluation. Use the connected concepts below as starting points, not as a keyword checklist.
Research this topic
Explore the main themes, entities and connections around Recommender system. Start with the topic map, then use the sections below for research and deeper semantic analysis.
Explore this topic
Start with a few of the strongest sections from the source topic. These are research directions, not a list of keywords you must use.
Approaches
22 related topics
Evaluation
21 related topics
Technologies
13 related topics
Artificial intelligence applications in recommendation
Artificial intelligenceNatural language processingStatistical distanceArtificial neural networkBlack-box
9 related topics
Key facts & relationships
High-confidence facts extracted from structured source data. Use them as anchors for further research.
Topics to explore
A structured outline of related entities, concepts and subtopics. Open any item to build a new map centered on it.Browse the full topic structure. Each item opens a new analysis centered on that subject.
Overview
- Social media
- Information filtering system
- Streaming services Streaming service
- Machine learning
- Decision-making processes Decision-making process
- Playlist
- E-commerce
- Online dating
- Software
- Platform Computing platform
- Metadata
- Websites Website
- Mobile devices Mobile device
- Set-top boxes
- Academic journal
- Collaborative filtering
- Knowledge-based systems
- Last.fm
- Pandora Radio
- Music Genome Project
- Cold start Cold start (recommender systems)
- Search algorithms Search algorithm
- Gonzalez v. Google Gonzalez v. Google LLC
- Dot product
- Cosine similarity
History
- Elaine Rich
- Jussi Karlgren
- SICS
- Pattie Maes
- Paul Resnick
- ACM Software Systems Award
- Beel Joeran Beel?action=edit&redlink=1
Approaches
- Predictions Prediction
- K-nearest neighbor K-nearest neighbors algorithm
- Pearson Correlation
- Cold start Cold start (computing)
- Multi-armed bandit algorithm Multi-armed bandit
- Social networking services Social networking service
- User profile
- Information retrieval
- Information filtering
- Tf–idf
- Vector space
- Bayesian Classifiers Naive Bayes classifier
- Cluster analysis
- Decision trees
- Artificial neural networks
- Text mining
- Sentiment analysis
- Multimodal sentiment analysis
- Deep learning
- Knowledge engineering
- Knowledge-based Knowledge base
- Netflix
Technologies
- YouTube
- Recurrent neural networks Recurrent neural network
- Transformer Transformer (deep learning architecture)
- Reinforcement learning
- Supervised learning
- Smartphones Smartphone
- Uber
- Lyft
- Sequential transduction Seq2seq
- Cardinality
- Self-attention Attention (machine learning)
- Traditional neural network layers Neural network (machine learning)
- Foundation models Foundation model
The Netflix Prize
- Netflix Prize
- Gravity R&D
- RecSys community ACM Conference on Recommender Systems
- Internet Movie Database (IMDb) IMDb
- Video Privacy Protection Act
- Federal Trade Commission
Evaluation
- Effectiveness
- Evaluations Evaluation
- Online evaluations (A/B tests) A/B testing
- Mean squared error
- Root mean squared error
- Precision and recall
- Discounted cumulative gain (DCG) Discounted Cumulative Gain
- Highly criticized Accuracy barrier
- Conversion rate
- Click-through rate
- User profiles
- Data privacy Information privacy
- Profiling Profiling (information science)
- Personalization
- Serendipity
- Reproducibility crisis
- RecSys Challenge RecSys Challenge?action=edit&redlink=1
- Ekstrand Michael Ekstrand?action=edit&redlink=1
- Konstan Joseph A. Konstan
- Said Alan Said?action=edit&redlink=1
- Bellogín Alejandro Bellogín?action=edit&redlink=1
Artificial intelligence applications in recommendation
Advanced semantic analysis
Deeper signals for content research, entity SEO and topical coverage. The plain-language headings explain what each technical view is useful for.
How this topic connects Entity context
Quick relationship hints grouped by predicate. Useful for spotting recurring semantic connections around the current entity.See the strongest relationship patterns around the current topic before diving into the raw triples.
Recommender system
Top relations
related to Further reading · 49
Recommender system → AAAI-2002, Alexander Felfernig, Algorithms, An Introduction, Archived, Artificial Intelligence, August, Bell, Bhasker, Canada, Chicago Press, Chris Volinsky, Computing Taste, Content-Boosted Collaborative Filtering, CUP, Dietmar, E-Commerce, Edmonton, Eighteenth National Conference, Gerhard Friedrich
related to Reproducibility · 25
Recommender system → Adomavicius, As, Bellogín, By, Deep, Ekstrand, Hence, IJCAI, In, KDD, Konstan, Machine Learning, More, Moreover, Recommender, Recommender Systems, RecSys, RecSys Challenge, Said, SIGIR
related to history · 16
Recommender system → ACM Software Systems Award, Another, Bellcore, Columbia University, Depending, Elaine Rich, GroupLens, Grundy, Her, Jussi Karlgren, MIT, Pattie Maes, Paul Resnick, She, SICS, Will Hill
related to The Netflix Prize · 12
Recommender system → As, Bell, BellKor's Pragmatic Chaos, From, Netflix, Netflix Prize, On, One, September, The, This, US
related to Collaborative filtering · 10
Recommender system → After, At, By, Collaborative, For, Left, One, Right, The, These
related to Alternative implementations · 9
Recommender system → Gonzalez, Google Supreme Court, In, LensKit, Of, RecBole, ReChorus, Recommender, RecPack
related to Example · 8
Recommender system → As, Last, Music Genome Project, Pandora, Pandora Radio, The, This, User
related to Performance measures · 8
Recommender system → A/B, DCG, Diversity, Evaluation, However, Netflix Prize, The, To
related to Session-based recommender systems · 7
Recommender system → Amazon, Domains, Most, Session-based, Techniques, These, YouTube
related to Content-based filtering · 6
Recommender system → Another, Content-based, In, It, These, This
Important terminology Word statistics
Frequent words and multi-word phrases across the lead, headings, infobox and body. Useful for terminology coverage.Use these terms to understand the vocabulary surrounding the topic, not as a checklist for keyword stuffing.
Important terminology
recommender systems user recommendation system recommendations users items filtering content collaborative data approaches item used information content-based learning based methods
Entity relationships Subject–Predicate–Object triples
Extracted RDF-like relationships with confidence and source. The table includes structured facts and lower-confidence contextual relations.| Subject | Predicate | Object | Confidence | Src |
|---|---|---|---|---|
| knowledge-based systems | instance of | as well as other systems | 0.80 | text |
| movies without requiring an | instance of | they generate recommendations using this neighborhood.The collaborative filtering approach does not rely on machine analyzable content and therefore it is capable of accurately… | 0.80 | text |
| Bayesian Classifiers | instance of | Simple approaches use the average values of the rated item vector while other sophisticated methods use machine learning techniques | 0.80 | text |
| cluster analysis | instance of | Simple approaches use the average values of the rated item vector while other sophisticated methods use machine learning techniques | 0.80 | text |
| decision trees | instance of | Simple approaches use the average values of the rated item vector while other sophisticated methods use machine learning techniques | 0.80 | text |
| and artificial neural networks in order to estimate the probability that the user is going to like the item.A key issue with content-based filtering is whether the system can learn user preferences from users' actions regarding one content source | instance of | Simple approaches use the average values of the rated item vector while other sophisticated methods use machine learning techniques | 0.80 | text |
| use them across other content types | instance of | Simple approaches use the average values of the rated item vector while other sophisticated methods use machine learning techniques | 0.80 | text |
| cold start | instance of | These methods can also be used to overcome some of the common problems in recommender systems | 0.80 | text |
| the sparsity problem | instance of | These methods can also be used to overcome some of the common problems in recommender systems | 0.80 | text |
| as well as the knowledge engineering bottleneck in knowledge-based approaches.Netflix uses a hybrid recommender systems to make recommendations by comparing the watching | instance of | These methods can also be used to overcome some of the common problems in recommender systems | 0.80 | text |
| searching habits of similar users | instance of | These methods can also be used to overcome some of the common problems in recommender systems | 0.80 | text |
| recurrent neural networks | instance of | Techniques for session-based recommendations are mainly based on generative sequential models | 0.80 | text |
No triples extracted yet.
Related concept clusters Concept neighborhoods
Clusters of nearby vocabulary surrounding the topic. Scan them for adjacent concepts and language you may have missed.These clusters group vocabulary that occurs around closely connected concepts in the source material.
Connections between topic areas Semantic bridges
Bridge nodes connect otherwise separate parts of the map. Expand a row to inspect the topic groups on each side.Bridges can reveal useful research angles that are easy to miss in a flat list of related terms.
Map overview Semantic statistics
Number of nodes, edges, triples, density and central hubs. Use it to gauge the size and connectivity of the map.Recommender system
Nodes111
Edges110
Triples218
Avg. degree1.98
Density0.018018
Components1
For writers, content strategists, SEOs, marketers and creators — from quick topic research to advanced semantic analysis.