On exploiting classification taxonomies in recommender systems
AI Communications - Recommender Systems
| Hi-index | 0.00 |
In this paper we address the problem of using bet selections of a large number of mostly non-expert users to improve sports betting tips. A similarity based approach is used to describe individual users' strategies and we propose two different scoring functions to evaluate them. The information contained in users' bet selections improves on using only bookmaker odds. Even when only bookmaker odds are used, the approach gives results comparable to those of a regression-based forecasting model.