Dynamic Valuation of Delinquent Credit-Card Accounts

Chehrazi, Naveed; Weber, Thomas A.

doi:10.2139/ssrn.1868581

Cited by 4 publications

(6 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second merit of our model is its ability to allow irregular time interval in data when learning complex serial dependence in high dimensional time series. Our findings coincide with the study of Chehrazi and Weber (2015) where self-and cross-excited Hawkes process captures dependencies between the arrival times of repayment events. The authors show that it is essential to capture the dependence structure when account-level data is used either for valuation or forecasting.…”

Section: Literature Reviewsupporting

confidence: 90%

“…Our approach to addressing this issue is to propose a specially-designed conditional loss objective in order to incorporate domain knowledge into the system. Specifically, the ability and the willingness to repay are considered as two significant loan determinants defaults (Lee 1991, Chehrazi andWeber 2015) in credit risk management.…”

Section: Our Contributionmentioning

confidence: 99%

“…Here, we propose to construct the default probability based on three major determinants of loan defaults (Lee 1991, Chehrazi andWeber 2015): the objective risk (the ability to repay), the subjective risk (the willingness to repay), and the behavioral risk (the risk neither objective nor subjective). In probability, we formulate the default probability as follows, P d := P (b|a, w)P (a)P (w),…”

Section: Conditional Lossmentioning

confidence: 99%

See 2 more Smart Citations

Neural Learning of Online Consumer Credit Risk

Wang

Zhang³

2019

SSRN Journal

View full text Add to dashboard Cite

This paper takes a deep learning approach to understand consumer credit risk when e-commerce platforms issue unsecured credit to finance customers' purchase. The "NeuCredit" model can capture both serial dependences in multi-dimensional time series data when event frequencies in each dimension differ. It also captures nonlinear cross-sectional interactions among different time-evolving features. Also, the predicted default probability is designed to be interpretable such that risks can be decomposed into three components: the subjective risk indicating the consumers willingness to repay, the objective risk indicating their ability to repay, and the behavioral risk indicating consumers' behavioral differences. Using a unique dataset from one of the largest global e-commerce platforms, we show that the inclusion of shopping behavioral data, besides conventional payment records, requires a deep learning approach to extract the information content of these data, which turns out significantly enhancing forecasting performance than the traditional machine learning methods.

show abstract

Section: Literature Reviewsupporting

confidence: 90%

Section: Our Contributionmentioning

confidence: 99%

Section: Conditional Lossmentioning

confidence: 99%

See 1 more Smart Citation

Neural Learning of Online Consumer Credit Risk

Wang

Zhang³

2019

SSRN Journal

View full text Add to dashboard Cite

show abstract

“…As the loan volume grows, major P2P lending platforms experience an increase in defaults. However, they have limited options for loan recovery operations (Chehrazi and Weber 2015). 1 Common practices include frequent reminders and offering financial incentives (waiving delay fees or interest payments), which have proved either ineffective or too costly; more effective autonomous collection tactics are urgently required (Luo et al., 2019).…”

Section: Introductionmentioning

confidence: 99%

Can Social Notifications Help to Mitigate Payment Delinquency in Online Peer‐to‐Peer Lending?

Wang

et al. 2021

Production and Operations Management

View full text Add to dashboard Cite

Payment management is an operations management challenge in online peer‐to‐peer (P2P) lending. It is critical to control the cost of debt collection incurred in late repayments and defaults. We study whether and how a platform can leverage on borrowers’ social connections and use automatic social notifications in regulating repayment behavior. In collaboration with a large online P2P lending platform, we conduct a randomized field experiment to investigate the effect of social notifications targeted at different contact groups (core‐circle and peripheral‐circle groups). Our results indicate that notifying social contacts of a delinquent regarding the overdue payment significantly improves the repayment rate. Compared with the control group in which no notification messages are sent to social contacts, notification‐triggered social sanctions and social support reduce the default rate by more than 50% in both core‐circle and peripheral‐circle groups. Furthermore, we find that social notifications targeted at peripheral‐circle social contacts are only effective in the short term, and its effectiveness decreases with repeated use. By contrast, social notifications targeted at core‐circle social contacts have a lasting effect.

show abstract

“…Self-exciting processes date back at least to the 1960s [Bartlett (1963), Kerstan (1964)]. The applicability of self-exciting point processes for modeling and analyzing time-series data has stimulated interest in diverse disciplines, including seismology [Ogata (1988[Ogata ( , 1998], criminology [Porter and White (2012), Mohler et al (2011), Egesdal et al (2010, Lewis et al (2010), Louie, Masaki and Allenby (2010)], finance [Chehrazi and Weber (2011), Aït-Sahalia, Cacho-Diaz and Laeven (2010), Bacry et al (2013), Filimonov and Sornette (2012), Embrechts, Liniger and Lin (2011), Hardiman, Bercot and Bouchaud (2013)], computational neuroscience [Johnson (1996), Krumin, Reutsky and Shoham (2010)], genome sequencing [Reynaud-Bouret and Schbath (2010)] and social networks [Crane and Sornette (2008), Mitchell and Cates (2010), Simma and Jordan (2010), Masuda et al (2012), Du et al (2013)]. These models appear in so many different domains because they are a natural fit for time-series data where one would like to predict discrete events in time, and where the occurrence of a past event gives a temporary boost to the probability of an event in the future.…”

mentioning

confidence: 99%

Reactive point processes: A new approach to predicting power failures in underground electrical systems

Ertekin¹,

Rudin²,

McCormick³

2015

Ann. Appl. Stat.

View full text Add to dashboard Cite

Reactive point processes (RPP's) are a new statistical model designed for predicting discrete events, incorporating self-exciting, self-regulating, and saturating components.The self-excitement occurs as a result of a past event, which causes a temporary rise in vulnerability to future events. The self-regulation occurs as a result of an external "inspection" which temporarily lowers vulnerability to future events. RPP's can saturate when too many events or inspections occur close together, which ensures that the probability of an event stays within a realistic range. RPP's were developed to handle an important problem within the domain of electrical grid reliability: short term prediction of electrical grid failures ("manhole events"), including outages, fires, explosions, and smoking manholes, which can cause threats to public safety and reliability of electrical service in cities. For the self-exciting, self-regulating, and saturating elements of the model, we develop both a nonparametric estimation strategy and introduce a class of flexible parametric functions reflecting how the influence of past events and inspections on vulnerability levels gradually fades over time. We use the model to predict power grid failures in Manhattan over a short term horizon.

show abstract

Dynamic Valuation of Delinquent Credit-Card Accounts

Cited by 4 publications

References 72 publications

Neural Learning of Online Consumer Credit Risk

Neural Learning of Online Consumer Credit Risk

Can Social Notifications Help to Mitigate Payment Delinquency in Online Peer‐to‐Peer Lending?

Reactive point processes: A new approach to predicting power failures in underground electrical systems

Contact Info

Product

Resources

About