"In this paper, we apply the multinomial logit regression and decision tree approaches to examine the critical deciding factors that affect auditor choice decisions. We first examine the relationship between the auditor choice and firm specific factors. In order to get deeper insights about the association between auditor choice and firm's characteristics, this paper employs the decision tree approach, a data mining technique, to explore the priority of variables affecting audit choices. The decision tree approach is an innovative tool that can help researchers choose between alternative options and investigate the possible outcomes of choosing options. To the best of our knowledge, this study is one of few studies that use the decision tree techniques to investigate the sequential deciding factors of audit choice decision. By applying both the regression and CART approaches, we find that auditor choice is affected first by agency conflict, and then by operating efficiency consideration, funding needs, and operating performance consideration sequentially.