A Framework for a Large-Scale B2B Recommender System
- Publisher:
- IEEE
- Publication Type:
- Conference Proceeding
- Citation:
- Proceedings of IEEE 14th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2019, 2019, 00, pp. 337-343
- Issue Date:
- 2019-11-01
Open Access
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is open access.
The aim of a recommender system is to suggest relevant items in order to improve purchasing experience and minimise information overload. Despite extensive research in the area of B2C recommender systems, business-to-business (B2B) distributors can not directly benefit from the results. Mainly because the data from these large scale retailers is not publicly available to researchers and also their problems are not widely known to the outside world. These companies have complex structures for their items and customers, e.g. the huge number of items and customers leading to data sparsity or the high level of accuracy required in recommending safety items. Furthermore, one of the key requirements for such businesses is bulk recommendations to be able to meet their market demands. A unique hybrid approach to recommendation with an emphasis on knowledge components is needed for such businesses. It is critical to have a careful analysis of item-category specific features for any recommendation as well as the customer context. In this paper, we propose a large scale B2B recommender framework to address the above requirements.
Please use this identifier to cite or link to this item: