A novel recommendation method based on general matrix factorization and artificial neural networks
- Submitting institution
-
University of Brighton
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 7155148
- Type
- D - Journal article
- DOI
-
10.1007/s00521-019-04534-w
- Title of journal
- Neural Computing and Applications
- Article number
- -
- First page
- 12327
- Volume
- 32
- Issue
- -
- ISSN
- 1433-3058
- Open access status
- Compliant
- Month of publication
- October
- Year of publication
- 2019
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 1
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Improving the accuracy of recommender systems in cases of high frequency, low relevance user-item biases, data specificities and individual operational user patterns is essential to the success of e-commerce, e-searching and marketing. This paper is significant because it proposes an approach that improves accuracy in e-commerce recommender systems while simultaneously reducing maintenance which is usually an expensive bottleneck in applied recommender systems. The matrix factorisation foundation from this paper has been picked up by the authors of CReS (Thaipisutikul and Shih, Neural Comput. & Applic. 2021) who have benchmarked it and developed it into a context recommender system.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -