Our technologies are able to analyze customer behaviors and provide personalized automatic services. We take two directions: (1) Establish a customer behavior prediction and recommendation system by analyzing consumption records, exploring behavior features, and strengthening the link between marketing strategies and behavior analysis; (2) Collaborative EDM subjects generation by analyzing the relationship between customers’ click records and consumption for understanding the relationship between customer intentions and financial products, and for generating personalized marketing strategies.

One of our research results has been published on the ACM WSDM, one under review on the ACM TIST, and two on the AAAI 2020. In terms of benchmark of quantitative metrics, our behavioral analysis and recommendation models outperform random forest and other base models by 40％. The increase in the proportion of customer spending increased by 2.87 times. The conversion rate of promotion considering consumer behavior reached 48.95％. The TemPEST model developed by us outperforms the BiSET model, which is also for the title generation, by 16％. Our PORL-HG is considered to be more attractive by 63.1％.

The development of our technologies is through cooperation with KKDAY and E-Sun Bank, and the use of its spatio-temporal database, clicks and comments database, social interaction database, etc., to explore the technologies required for e-commerce engagement modules. By analyzing user browsing consumption records and other available datasets to explore important features like customer preferences and behavior patterns, our model is able to generate EDM content, and to deliver to target customers at the right time, and hence it allows to materialize the actual occurrence of purchase behavior.

線上展網址：
https://tievirtual.twtm.com.tw/iframe/9ffca11b-dd3f-4b04-af26-1c2888935dba?group=23bfb1fa-dd5b-4836-81a1-4a1809b1bae5&lang=en