Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
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.
- Host: GitHub
- URL: https://github.com/mattweingarten/daem
- Owner: mattweingarten
- Created: 2022-08-30T21:09:55.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2022-08-30T21:10:53.000Z (over 2 years ago)
- Last Synced: 2024-12-16T20:30:43.689Z (about 1 month ago)
- Language: Python
- Size: 3.59 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0