Customer Selection Model with Grouping and Hierarchical Ranking Analysis

The purpose of this study was to build a customer selection model based on 20 dimensions, including customer codes, total contribution, assets, deposit, profit, profit rate, trading volume, trading amount, turnover rate, order amount, withdraw amount, withdraw rate, process fee, process fee submitted, process fee retained, net process fee retained, interest revenue, interest return, exchange house return I and exchange house return II to group and rank customers. The traditional way to group customers in securities or futures companies is simply based on their assets. However, grouping customers with respect to only one dimension cannot give us a full picture about customers' attributions. It is hard to group customers' with similar attributions or values into one group if we just consider assets as the only grouping criterion. Nowadays, securities or futures companies usually group customers based on managers' experience with lack of quantitative analysis, which is not effective. Therefore, we use kmeans unsupervised learning methods to group customers with respect to significant dimensions so as to cluster customers with similar attributions together. Grouping is our first step. It is the horizontal analysis in customer study. The next step is customer ranking. It is the longitudinal analysis. It ranks customers by assigning each customer with a certain score given by our weighted customer value calculation formula. Therefore, by grouping and ranking customers, we can differentiate our customers and rank them based on values instead of blindly reaching everyone.