Skip to content

PyTorch implementation of GRU4Rec, SQN and SMORL with evaluation framework covering Hit-Ratio, NDCG, Novelty, Diversity and Repetitiveness metrics for top-k recommendations.

License

Notifications You must be signed in to change notification settings

PatrickSVM/Session-Based-Recommender-Models

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Session Based Recommender Models

Embedding Analysis Example

Example Visualization from Embedding Analysis

This repository contains the python package developed for my master thesis "Incorporating Reinforcement Learning into Supervised Sequential Recommender Models" in cooperation with IKEA.

At its core, the package contains the PyTorch implementations of the three models - GRU4Rec, SQN and SMORL - together with the according evaluation framework covering Hit-Ratio, NDCG, Novelty, Diversity and Repetitiveness metrics. It forms the basis for all experiments and results provided in the thesis.

Abstract

In the context of the significant expansion of e-commerce, Recommender Systems have become important tools for businesses, enhancing customer engagement through the personalization of product recommendations. This thesis investigates the integration of Reinforcement Learning concepts into Supervised Learning frameworks, aiming to foster more accurate, novel and diverse recommendations. This study is conducted within the context of IKEA's Inspirational Feed, a feed of home-furnishing inspirations provided across IKEA's digital platforms. For this purpose, a detailed analytical comparison of three different session-based, sequential recommendation models is executed. This includes the purely supervised GRU4Rec model, as well as two hybrid approaches — SQN and SMORL — which combine Supervised Learning with the Double Q-Learning algorithm from Reinforcement Learning. The primary focus lies on SMORL, a multi-objective model explicitly designed to enhance the diversity and novelty of recommendations. As the results of this analysis reveal, all three models were able to effectively learn interrelationships among IKEA's products and Inspirational Feed images and provided reasonable next image recommendations. However, no evidence was found that the incorporation of Reinforcement Learning in the learning process helped models to improve recommendations. The thesis concludes by proposing potential directions for future research and potential modifications to the experimental design that could possibly alter these findings.

Usage

The package can be installed via pip install .

All necessary dependencies can be found in the environment-file.



Example prediction batches of all three models

Example prediction batches of all three model classes

About

PyTorch implementation of GRU4Rec, SQN and SMORL with evaluation framework covering Hit-Ratio, NDCG, Novelty, Diversity and Repetitiveness metrics for top-k recommendations.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages