Predicting the Outcome of a Debt Collection Process Using Bayesian Networks

2022 | HICSS | Citations: 0

Authors: Köhler, Benedikt; Fromm, Hansjörg

Abstract: Many companies rely on professional debtcollection agencies to handle their outs ... Expand

Abstract: Many companies rely on professional debtcollection agencies to handle their outstanding debts. These agencies conduct a debt collection process consisting of successive, escalating actions with the aim of getting a debtor to settle an overdue claim. The sequence of actions is administered by agents who often have to make decisions on a case-by-case basis. This requires understanding of complex data and making decisions under uncertainty. This decision-making process has hardly been investigated so far. We are proposing Bayesian networks as the analytical basis for a decision support system. Bayesian networks are strong in dealing with uncertainties. They can be used for both predicting the success of a case and making recommendations on actions. The evaluation shows that Bayesian networks have a very good predictive performance which gets even better as the process evolves. With this instrument, the agents can make better-informed decisions in the debt collection process. Collapse

Topics: decision support system telephone analytical information system

Methods: Bayesian network computational algorithm machine learning sensitivity analysis naïve bayes

“She is not just a computer”: Gender Role of AI Chatbots in Debt Collection

2020 | International Conference on Information Systems | Citations: 0

Authors: Guo, Yiting; Yin, Ximing

Abstract: Chatbots have been empowered by Artificial Intelligence (AI) and rapidly applied ... Expand

Abstract: Chatbots have been empowered by Artificial Intelligence (AI) and rapidly applied to many industries. There is a call for more understanding of the effect of chatbots’ social cues on business outcomes. This paper investigates how does the choice of chatbots’ voice gender impacts customers’ intention to repay overdue debt. Prior studies on gender differences have conflicting implications. Employing unique real business dataset, we find that for male customers, they are more willing to repay when served by female chatbots. However, female customers have no preference for the gender of chatbots. We finally explain the effect of chatbot gender in ten gender-stereotypical attributes (e.g., forceful and assertive of masculinity, gentle and warm of femininity). The results demonstrate that masculine attributes have significant negative effects on both male and female customers while feminine attributes only have significant (positive) effects on male customers. Based on the results, we further discuss the theoretical contributions and managerial implications. Collapse

Topics: artificial intelligence robotic behavioral intention usability human computer interaction

Methods: chatbot experiment laboratory experiment descriptive statistic econometric modeling

Theories: role theory

Personalizing Debt Collections: Combining Reinforcement Learning and Field Experiment

2020 | International Conference on Information Systems | Citations: 0

Authors: Yang, Tracy; Lu, Tian; Li, Beibei; Xianghua, Lu

Abstract: Artificial intelligence (AI) brings about opportunities to revolutionize financi ... Expand

Abstract: Artificial intelligence (AI) brings about opportunities to revolutionize financial services. We focus on the loan debt collection context wherein collectors usually leverage privateinformation-based actions and follow a strict sequential collection strategy. We apply reinforcement learning to optimize the collection strategy with fine-grained data. The optimized results suggest loan platforms generally use collection actions less (by 63.39%) and more cautiously. Further borrower profiling analyses underscore the importance of personalization in debt collections. Moreover, we demonstrate the vast economic value of personalization in debt collections as it not only improves loan recovery rate (by 8.11%), but also enables platforms to allocate limited resources to cover more delinquent loans. A field experiment helps validate and quantify the economic value of the optimization algorithm in a real-world context. This study contributes to the literature of AI in FinTech, debt collections, and privacy. The findings also offer concrete, actionable, and costeffective practical and policy implications. Collapse

Topics: privacy artificial intelligence usability personalization electronic finance

Methods: field experiment computational algorithm parametric test Student's t-test descriptive statistic