Skip to content

Latest commit

 

History

54 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 

Repository files navigation

Part 1

Recommender System for Dating Website

The project is a dating website recommendation system.

Here we build two collaborative filtering models, KNN and SVD. We select the most popular 10000 male and 1000 female users' ratings from Czech dating site libiseti in 2006 http://www.occamslab.com/petricek/data/ (where poplairy is calculated by the number of rating received).

The goal is to provide users with personalized dating candidates, according to the rating history of a user to the others. This project implements collaborative filtering algorithms in two parts: "building from scratch" and "using Surprise package." Each part would construct two models based on neighborhood-based or model-based algorithms. Through tuning the hyper parameter, evaluating the coverage, and calculating the accuracy, the models are continuously optimized.

Part 2

Recommendation System for Amazon Apps

Columbia University E4571 Personalization: Theory & Application

Project Part 2 - Modern Personalization Frameworks and Algorithms

Team Members:

Pin-Hao Chen - UNI: phc2121
Leshen Sui - UNI: ls3452
Siwen Tang - UNI: st3101
Jingyi Wang - UNI: jw3562

Contents:

About

Personalization Project // Amazon App Review Recommendation

Resources

Stars

9 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages