There are 0 repository under movie-lens topic.
recommender systems algorithm
The movie recommender is based on the Collaborative Filtering approach, and creates predictions for movie ratings with Matrix Factorization technique, more precisely, the SVD (Singular Value Decomposition) algorythm of SurPRISE library. Trained on 'small' dataset of MovieLens.
Data pipeline implementation to predict the average mark of a film from its features, using ML techniques
This work involved building a pipeline of recommender systems comprising of Popularity based recommender, KNN similarity based Clustering recommender, Item-Item association based recommender, Bi-Partite graph based association recommender, Neural Graph based Collaborative Filtering and Neural Embedding based Collaborative filtering.
The final project created for Optimization for Data Science course
Extended version of the collaborative filtering recommender systems(RecSys) written in PyTorch
This is the Movielens Capstone project for the Data Science Course offered by Harvard.
NCF Paper Implementation (Pytorch)
This project analyzes movie data using MongoDB and Matplotlib, deriving insights through preprocessing, visualization, trend analysis, and text analysis techniques. It aims to uncover patterns in movie preferences and production trends.
Predicting ratings of a movie using ridge regression and lasso regression trained on the Movie Lens database
Leverage score based Tensor Completion algorithm, SPLATT