RecSys2019_DeepLearning_Evaluation

Visit Tool

RecSys2019_DeepLearning_Evaluation is an Open Source research tool that provides code and data for evaluating neural recommendation approaches. It allows researchers to replicate findings and benchmark deep learning models in recommender systems.

Claim this tool

No Views Yet

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is RecSys2019_DeepLearning_Evaluation?

RecSys2019_DeepLearning_Evaluation is an open-source repository developed by Maurizio Ferrari Dacrema, a postdoctoral researcher at Politecnico di Milano. It provides the source code and experimental results for several articles published in prominent conferences like RecSys 2019, ACM TOIS 2021, CIKM 2020, and IJCAI 2020. The repository focuses on evaluating and analyzing deep learning models in recommender systems, offering implementations of various deep learning and baseline algorithms. It includes tools for data management, hyperparameter optimization, and evaluation metrics, making it a valuable resource for academic research in the field of recommender systems.

Best used for

Ideal for professors and researchers who need to evaluate the performance of neural recommendation approaches, replicate published research findings, and benchmark various deep learning models. Especially valuable for academic studies focused on the reproducibility and progress in recommender systems research.

Common actions

evaluate recommendation algorithms

replicate research findings

benchmark deep learning models

optimize hyperparameters

workflowslow-code/no-codecollaborationopen-sourceautomated workflowdeepfakeface swappinggithub copilot"AI Agents"

Capabilities

Key features

Deep learning algorithm implementations
Baseline algorithm implementations
Hyperparameter optimization
Evaluation metrics
Data management

Target Audience

professor

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What kind of algorithms are included in this repository?

The repository includes implementations of various deep learning algorithms from conferences like RecSys, IJCAI, KDD, and SIGIR, as well as a comprehensive set of baseline algorithms such as KNN, Matrix Factorization, SLIM BPR, and EASE_R, covering both collaborative and content-based approaches.

How does the repository handle data for experiments?

The repository uses specific DataReader objects to gather data for experiments. It can load original data splits, automatically download datasets, or provide instructions for manual download. Preprocessed data is saved for future use, ensuring consistency across experiments.

Can I use this repository to optimize hyperparameters for my own models?

Yes, the repository includes a ParameterTuning folder with code for hyperparameter optimization. The SearchBayesianSkopt object performs Bayesian optimization for a given recommender instance and hyperparameter space, saving explored configurations and recommendation quality.

Trending

Subcategories trending in Research & Education

Study Assistants Knowledge Management Course Creation Scientific Computing Summarization Language Learning

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce