Abstract—In this paper we focus on personalized recommendation algorithm for coupon deals, which face “cold start” problem at all times because they only have short time validity. As our dataset is from a private source, we first analyzed deal characteristics and found that deals under category “dining”, “wellness” and “activities” have a high probability of having the same keywords in the deal names, which suggests a repeated buying pattern. Then we computed the keyword associations from the dataset and found meaningful patterns. Based on the keyword association rules, we proposed a new recommendation algorithm which combines baseline algorithm and keyword association, resulting in significant improvement in percentage of hits, average rank and mean reciprocal rank.

Index Terms—association rules, coupon deals, keywords, personalized recommendation system, repeated buying pattern

Cite: Yi Huang, "Personalized Recommendation of Coupon Deals by Keywords Association Rules," Journal of Industrial and Intelligent Information, Vol. 4, No. 2, pp. 186-190, March 2016. doi: 10.18178/jiii.4.2.186-190