This is a repository containing a copy of a project I made for a course from NYU. It contains code and a report describing a modification of the matrix factorization method Alternating Least squares.

🎓 Final Project for Completing Bachelor Degree in Petra Christian University. Create Hybrid Recommender System for Interior Products and its Services using Data Implicit Feedback

The objective of the competition was to create the best recommender system for a book recommendation service by providing 10 recommended books to each user. The evaluation metric was MAP@10.

An anime recommendation engine that allows us to recommend anime based on a given anime title or a given user using Pyspark

Scalable Book Recommender System - Apache Spark ML Lib

Alternating Least Squares (ALS) recommender system

Recommender System 2019 Challenge PoliMi

This project looked at scalable machine learning for a movie recomemdantion set utilising ALS (alternative least squares) A NASA data set was used as a familiarisation to pySpark. The data was plotted using matplotlib.

Full stack machine learning music recommendation app using ALS collaborative filtering, built using Flask and PySpark

Recommender System project that uses Weighted Matrix Factorisation to learn user and items embeddings from a (sparse) feedbacks matrix, and uses them to perform user-specific suggestions

Simple Content based and Collaborative Filtering Algorithms implementaion

Movies suggestions using ALS (inspired Netflix Challenge)

Collaborative-filtering Recommender System using Spark Alternating Least Squares method

Repository for the Recommender Systems Challenge 2020/2021 @ PoliMi

A pure Python implementation of Alternating Least Squares (ALS)

ETL pipeline and Machine Learning model for recommending cryptocurrencies

A collaborative-filter-based music recommender machine

Matrix factorization for collaborative filtering using ALS specifically optimized for rank-1 approximation.

In this project, a Recommender System is built from 2 popular methods which are Content Based Filtering (Gensim and Cosine Similarity algorithms) and Collaborative Based Filtering (Alternating Least Square model in PySpark). Then, this recommender system is deployed onto Heroku cloud platform.

Recommender systems on MovieLens data using explicit ratings, and curated implicit feedback data.