基于行为和评分相似性的关联规则群推荐算法

Behavior and Score Similarity Based Algorithm for Association Rule Group Recommendation

使用关联规则推荐工具会遇到最优推荐规则选取难、规则信息不能充分利用等问题。利用较易获取的应用领域知识可有效解决这类问题。针对仅有商品名称和评分信息的推荐情形,提出一种基于行为和评分相似性的关联规则群推荐算法,该算法将规则及相应的评分信息视为推荐专家,将推荐结论相同的专家合并为一个专家组,利用客户行为和评分的双重相似性计算专家权重,并利用群决策的思想集结专家组的推荐意见,从而给出最佳推荐方案。最后通过实例和实验说明了该算法的可行性和有效性。

Applying the association rule recommendation tool often meets the hardness of selection for optimal rule,inadequate utilization of rule information.Using easily obtained background knowledge can solve these problems.Aiming at the situation that only contains commodity＇ s name and score information,this paper proposed a behavior and score similarity based association rule group recommendation algorithm,in which the rule with its scores is regarded as an expert,and the experts with same conclusion are grouped together and the expert weights are calculated based on both behavior similarity and score similarity.A better recommendation suggestion is reached by aggregating the recommendation opinions of the experts.The experimental example shows that the algorithm is feasible and effective.