Project Overview: Knowledge-based, Content-based and Collaborative Recommender systems are built on MovieLens dataset with 100,000 movie ratings.
-
Updated
Dec 31, 2022 - Jupyter Notebook
Project Overview: Knowledge-based, Content-based and Collaborative Recommender systems are built on MovieLens dataset with 100,000 movie ratings.
A book recommender system is a type of a type of recommendation system where we have to recommend similar books to the reader based on his interest. In this project, we will implement the populartity based recommender system and collabrative based recommender system to build a book recommender system.
Item-based collaborative filtering makes recommendations based on user-product interactions in the past.
Movie Recommendation System using Popularity, Content and Collaborative Based Recommendation methods
Content-based Movie Recommender System
The application uses content based filtering to make recommendations. For every movie selected, 12 recommendations are made based on their cosine similarity with the selected movie. An API feteches the poster image of the movie and displays them in an image grid to the user The database offers nearly 5000 movies to select from
MusicRecommendation for two song inputs, combining three different filtering.
Neural matrix factorization movie recommender paired with image similarity in poster design
The project used Python to create a personalized book recommendation system that analyzed users' past ratings on books to identify their preferences and patterns and suggested books that the user is likely to enjoy but has not read yet.
Movie Recommendation - Content Based
ExcelR_Assignment---Recommendation-System---Assignment---10
Comparison of 3 different recommender systems, i.e., multi-class classification, collaborative filtering, and deep-learn matrix factorization.
Using Matrix Factorization
Repo para el curso de Tópicos en Bases de Datos
Repositorio para las practicas de la asignatura Gestión de Información en la Web (parte Recuperación de Información) del Master en Ingeniería Informática de la UGR.
A product recommendation system build using Scala, Apache Spark and Play framework
An event recommendation system
This JavaScript engine recommends openings based on individual play style. Users can specify whether they are looking for an aggressive/passive opening or an open/closed game. They can also specify whether they like gambits and how deep into theory they'd like to go. Chess opening descriptions are scraped from Wikipedia.
Add a description, image, and links to the recommendation-system topic page so that developers can more easily learn about it.
To associate your repository with the recommendation-system topic, visit your repo's landing page and select "manage topics."