Recommendation as classification: using social and content-based information in recommendation
AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
An algorithmic framework for performing collaborative filtering
Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval
An entropy approach to unintrusive targeted advertising on the Web
Proceedings of the 9th international World Wide Web conference on Computer networks : the international journal of computer and telecommunications netowrking
Algorithms for association rule mining — a general survey and comparison
ACM SIGKDD Explorations Newsletter
Personalization of Supermarket Product Recommendations
Data Mining and Knowledge Discovery
E-Commerce Recommendation Applications
Data Mining and Knowledge Discovery
Integrating Web Usage and Content Mining for More Effective Personalization
EC-WEB '00 Proceedings of the First International Conference on Electronic Commerce and Web Technologies
Series of Dynamic Targeted Recommendations
EC-WEB '02 Proceedings of the Third International Conference on E-Commerce and Web Technologies
Web usage mining: discovery and applications of usage patterns from Web data
ACM SIGKDD Explorations Newsletter
Series of Dynamic Targeted Recommendations
EC-WEB '02 Proceedings of the Third International Conference on E-Commerce and Web Technologies
A framework for session based recommendations
EC-Web'05 Proceedings of the 6th international conference on E-Commerce and Web Technologies
| Hi-index | 0.00 |
Merchants often use marketing elements such as advertisements, coupons and product recommendations, to attract customers and to convert visitors to buyers. We present a model for making a series of recommendations during a customer session. The model comprises of the customer's probability of accepting a marketing element from a marketing spot and a reward for the marketing element. The probabilities can be estimated from customer history (such as traversals and purchases), while the reward values could be merchant specified. We propose several recommendation strategies for maximising the merchant's reward and analyse their effectiveness. Our experiments indicate that strategies that are dynamic and consider multiple marketing spots simultaneously perform well.