Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/mattweingarten/daem

Highly accurate Recommender Systems, including Collaborative Filtering, lie at the heart of a satisfactory customer experience and continuous user engagement for a plethora of large-scale online platforms. While Matrix Factorization is the most widely studied and applied Collaborative Filtering approach, there is evidence to suggest that linear techniques lack the complexity to sufficiently capture the underlying relationship between users and items. The use of neural networks like Autoencoders offers a potential remedy and may more accurately represent this relationship. In this work, we propose our Denoising Autoencoder Model (DÆM) for highly accurate Collaborative Filtering and show improvement over four evaluated state-of-the-art models.
https://github.com/mattweingarten/daem

Last synced: 18 days ago
JSON representation

Highly accurate Recommender Systems, including Collaborative Filtering, lie at the heart of a satisfactory customer experience and continuous user engagement for a plethora of large-scale online platforms. While Matrix Factorization is the most widely studied and applied Collaborative Filtering approach, there is evidence to suggest that linear techniques lack the complexity to sufficiently capture the underlying relationship between users and items. The use of neural networks like Autoencoders offers a potential remedy and may more accurately represent this relationship. In this work, we propose our Denoising Autoencoder Model (DÆM) for highly accurate Collaborative Filtering and show improvement over four evaluated state-of-the-art models.

Awesome Lists containing this project