A movie recommender which recommends the movies belonging to the genre that user has liked the most.

Last update: Mar 31, 2022

Overview

Content-Based-Movie-Recommender-System

This model relies on the similarity of the items being recommended.

(I have used Pandas and Numpy. However others may also use different libraries)

A content based recommender works with data that the user provides, either explicitly movie ratings for the MovieLens dataset. Based on that data, a user profile vector is generated, which is then used to make suggestions to the user.

As the user provides more inputs or takes actions on the recommendations, the weighted average vector of user becomes more accurate thus giving more accurate recommendations when data feeded is more.

Advantages :

Learns user's preferences

Highly personalized for the user

Disadvantages :

Low rated movie recommendation might occur if user choices were poor

Only genres watched and rated by user will be recommended and new genres will be hidden

User profile vector is highly static as the movie watched by user is mostly based on user's mentality and not user's previous history

A movie recommender which recommends the movies belonging to the genre that user has liked the most.

Related tags

Overview

Content-Based-Movie-Recommender-System

This model relies on the similarity of the items being recommended.

(I have used Pandas and Numpy. However others may also use different libraries)

A content based recommender works with data that the user provides, either explicitly movie ratings for the MovieLens dataset. Based on that data, a user profile vector is generated, which is then used to make suggestions to the user.

As the user provides more inputs or takes actions on the recommendations, the weighted average vector of user becomes more accurate thus giving more accurate recommendations when data feeded is more.

Advantages :

Learns user's preferences

Highly personalized for the user

Disadvantages :

Low rated movie recommendation might occur if user choices were poor

Only genres watched and rated by user will be recommended and new genres will be hidden

User profile vector is highly static as the movie watched by user is mostly based on user's mentality and not user's previous history

Owner

Srinivasan K

This is our implementation of GHCF: Graph Heterogeneous Collaborative Filtering (AAAI 2021)

Incorporating User Micro-behaviors and Item Knowledge 59 60 3 into Multi-task Learning for Session-based Recommendation

RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems

Bert4rec for news Recommendation

Persine is an automated tool to study and reverse-engineer algorithmic recommendation systems.

Accuracy-Diversity Trade-off in Recommender Systems via Graph Convolutions

A library of metrics for evaluating recommender systems

Bundle Graph Convolutional Network

The implementation of the submitted paper "Deep Multi-Behaviors Graph Network for Voucher Redemption Rate Prediction" in SIGKDD 2021 Applied Data Science Track.

Spark-movie-lens - An on-line movie recommender using Spark, Python Flask, and the MovieLens dataset

The source code for "Global Context Enhanced Graph Neural Network for Session-based Recommendation".

A Python scikit for building and analyzing recommender systems

Global Context Enhanced Social Recommendation with Hierarchical Graph Neural Networks

Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer

Attentive Social Recommendation: Towards User And Item Diversities

Recommender System Papers

Learning Fair Representations for Recommendation: A Graph-based Perspective, WWW2021

[ICDMW 2020] Code and dataset for "DGTN: Dual-channel Graph Transition Network for Session-based Recommendation"

Knowledge-aware Coupled Graph Neural Network for Social Recommendation

Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk