top-n-recommendations

An Open-source Toolkit for Deep Learning based Recommendation with Tensorflow.

Recommender system and evaluation framework for top-n recommendations tasks that respects polarity of feedbacks. Fast, flexible and easy to use. Written in python, boosted by scientific python stack.

Must-read Papers for Recommender Systems (RS)

rectorch is a pytorch-based framework for state-of-the-art top-N recommendation

Accompanying code for reproducing experiments from the HybridSVD paper. Preprint is available at https://arxiv.org/abs/1802.06398.

DataSets links for recommender systems research, in particular for transfer learning, user representation, pre-training,lifelong learning, cold start recommendation

Machine learning- based solution to the problem of duplicity in the bug reports repository.

This is the repository for the Master of Science thesis titled "GAN-based Matrix Factorization for Recommender Systems".

TensorFlow2 Implementation of "Neural Attentive Item Similarity Model for Recommendation"

The Implementation of "FISM: Factored Item Similarity Models for Top-N Recommender Systems"

A Worrying Reproducibility Study of Intent-Aware Recommendation Models

Customer segmentation of retail data using PCA + K-Means, Agglomerative, and DBSCAN/HDBSCAN, with cluster profiling via radar charts and histograms, and cluster-based top-3 product recommendations.

Lightweight library for computing statistical features from weighted event sequences. Might be used in search ranking and feature extraction.

Top-N movie recommender on MovieLens 1M (1M ratings, 6,040 users) comparing mean/popularity baselines, Funk SVD, Surprise SVD, item-item collaborative filtering, and a Bayesian ensemble. Evaluates Precision/Recall/HitRate@10 plus subgroup performance by age and gender.

We share our code online": Why this is not enough to ensure reproducibility and progress in recommender systems research

A lightweight recommender that helps you discover your next learning resource. It blends patterns from similar users with content keywords, and explains each suggestion in the UI.

Implementation of z-scoREC and ImposeSVD for top-N recommendations