Consumer Default Research Articles

Employer Credit Checks: Poverty Traps Versus Matching Efficiency

Abstract We develop a framework to understand pre-employment credit screening as a signal from credit markets that alleviates adverse selection in labour markets. In our theory, people differ in both their propensity to default on debt and the profits they create for firms that employ them; in our calibrated economy, highly productive workers have a low default probability. This leads firms to create more jobs for those with good credit, which creates a poverty trap: an unemployed worker with poor credit has a low job finding rate, but cannot improve her credit without a job. This manifests as an endogenous loss in present-discounted wages that is typically taken as exogenous in quantitative models of consumer default. Banning employer credit checks eliminates the poverty trap, but pools job seekers and reduces matching efficiency: average unemployment duration rises by 2 days for high productivity workers and falls by 13 days for low-productivity workers.

LEGAL PROTECTION FOR E-COMMERCE TRANSACTION BUSINESS ACTORS IN THE ERA OF DIGITAL TRANSFORMATION IN INDONESIA

Digital transformation contributes to the growth of trade through electronic media (E-Commerce). This provides a great opportunity for business actors to develop their business and increases the chances of consumer default. One possible cause of payment failure is the transaction method that uses the Cash on Delivery method. This research aims to determine legal protection for business actors in buying and selling transactions via E-Commerce. The research method used is normative juridical with descriptive research specifications, data collection is carried out through documentary studies and literature studies, and data analysis is carried out qualitatively through deductive logical thinking. Legal protection for business actors against acts of default committed by consumers is generally regulated in the Civil Code and specifically regulated in the Electronic Transaction Information Law and Consumer Protection Law. The Civil Code explains that business actors have the right to receive payment if their goods reach consumers. If the consumer commits an act of default, the business actor can ask for compensation for losses caused by non-fulfillment of the agreement. Technically, the Consumer Protection Law does not fully protect the rights of business actors as parties to buying and selling transactions via E-Commerce. Because, since the publication of the Consumer Protection Law in 1999, the era of digitalization has not changed, so the existence of the Electronic Transaction Information Law complements this deficiency. There needs to be an update to the Consumer Protection Law to protect the rights of business actors. Without adequate regulations, it will cause new disruptions to the development of the Indonesian economy.

Consumer Default Risk Portrait: An Intelligent Management Framework of Online Consumer Credit Default Risk

Online consumer credit services play a vital role in the contemporary consumer market. To foster their sustainable development, it is essential to establish and strengthen the relevant risk management mechanism. This study proposes an intelligent management framework called the consumer default risk portrait (CDRP) to mitigate the default risks associated with online consumer loans. The CDRP framework combines traditional credit information and Internet platform data to depict the portrait of consumer default risks. It consists of four modules: addressing data imbalances, establishing relationships between user characteristics and the default risk, analyzing the influence of different variables on default, and ultimately presenting personalized consumer profiles. Empirical findings reveal that “Repayment Periods”, “Loan Amount”, and “Debt to Income Type” emerge as the three variables with the most significant impact on default. “Re-payment Periods” and “Debt to Income Type” demonstrate a positive correlation with default probability, while a lower “Loan Amount” corresponds to a higher likelihood of default. Additionally, our verification highlights that the significance of variables varies across different samples, thereby presenting a personalized portrait from a single sample. In conclusion, the proposed framework provides valuable suggestions and insights for financial institutions and Internet platform managers to improve the market environment of online consumer credit services.

The Effect Credit Monitoring Activities on Financial Reporting Quality of Private Banks in Ethiopia

This study examines the effect of credit monitoring activities on the financial reporting quality of private banks in Ethiopia. Using a quantitative research method with a positivist philosophical assumption, data were collected through a structured questionnaire from 90 respondents. The study finds that the independent variables, which include collateral information, business ratings information, customer credit status information, and consumer default information, have a positive effect on the financial reporting quality of private banks in Ethiopia. These findings emphasize the importance of effective credit monitoring activities to ensure accurate and reliable financial reporting in the banking sector.

Lending technologies and consumer defaults in times of crisis: Evidence from Brazil

We investigate the role of lending technologies in consumer credit defaults in Brazil before and during the COVID-19 pandemic. First, relationship borrowers are less likely to default than others before the pandemic. Second, this effect persists during the pandemic, but it becomes around 60 % smaller. Third, we document important heterogenous effects. Relationship borrowers of appliance finance default less during the pandemic than the ones of general-purpose cash loans. Finally, female relationship borrowers are less likely to default during the pandemic, plausibly because of the higher job uncertainty and the increase of informal jobs for Brazilian women during the COVID-19.

Tracking Deviceson Collateral Vehiclesby Financial Institutions Invadescustomer Privacyaccording To Privacy Protection Law

Financial institutions expect financing to be returned on time and adherethe terms of the agreement. Financial institutions profit from the ability to handle non-performing loans (NPL). The lower the level of NPL, the lower the risk and the higher the profit made by the financial institution. One way to mitigate risk is the capacity to take over the collateral for financing. One of the collaterals for financing is in the form of a vehicle. This vehicle is guaranteed by Fiduciarysecurity. If consumer default occurs, financial institutions can seize the collateral and use it to pay off the loan. Financial institutions employ a variety of strategies to ensure that collateral is quickly located in the event of a default. One method is to use technology to install a tracking device. This study scrutinizes the use of tracking devices by financial institutions from the perspective of consumer privacy protection. This normative legal research concludes that collaterals with Fiduciarysecurity are property of financial institutions prior to settlement. However, the installation of tracking devices on collateral vehicles might invade customer privacy. The customer has the option to objectthe installation of the device on the vehicle

Predictive Multiplicity in Probabilistic Classification

Machine learning models are often used to inform real world risk assessment tasks: predicting consumer default risk, predicting whether a person suffers from a serious illness, or predicting a person's risk to appear in court. Given multiple models that perform almost equally well for a prediction task, to what extent do predictions vary across these models? If predictions are relatively consistent for similar models, then the standard approach of choosing the model that optimizes a penalized loss suffices. But what if predictions vary significantly for similar models? In machine learning, this is referred to as predictive multiplicity i.e. the prevalence of conflicting predictions assigned by near-optimal competing models. In this paper, we present a framework for measuring predictive multiplicity in probabilistic classification (predicting the probability of a positive outcome). We introduce measures that capture the variation in risk estimates over the set of competing models, and develop optimization-based methods to compute these measures efficiently and reliably for convex empirical risk minimization problems. We demonstrate the incidence and prevalence of predictive multiplicity in real-world tasks. Further, we provide insight into how predictive multiplicity arises by analyzing the relationship between predictive multiplicity and data set characteristics (outliers, separability, and majority-minority structure). Our results emphasize the need to report predictive multiplicity more widely.

Handling of Consumer Defaults at PT Adira Finance from the Perspective of Islamic Economics Ethics

Defaults in motor vehicle loan agreements by consumers occur because of the consumptive nature of customer is not directly proportional to their income. In addition there is a bad faith from some consumer not to carry out their obligation as they should. The purpose of this study was to analyze the handling of defaults on motor vehicle agreements at PT Adira finance. This study used qualitative research method with field research. The result show that PT Adira Finance in dealing with the consumers default in motor vehicle loan agreements from the perspective of the Islamic business ethics has implemented several basic principles of business ethics in Islamic economics especially monotheism, free will, responsibility and truth. While the principle of balance and justice. PT. Adira Finance has not fully applied Islamic economic ethics, especially in term of writing of consumer debt that are eligible for assistance because they meet certain conditions such as going bankrupt

Credit Card Approval Prediction using Classification Algorithms

Abstract: Credit risk as the boards in banks basically revolves around determining the probability of default or the creditworthiness of a customer, collapse, and the cost, assuming it happens. It is important to consider key factors and anticipate the likelihood of consumer default, given the circumstances. This is where machine learning models come into play. This allows banks and large financial institutions to predict whether their customers will default on their loans. This project uses Python to create machine-learning models with the highest possible accuracy. First, we load the dataset and take a glimpse. The data set is a combination of mathematical and non-mathematical elements, with various ranges of values and some missing points. We pre-process the dataset so that the selected ML model meets high expectations.

Banking relationship and default priority in consumer credit: Evidence from Thai microdata

Banks play an important role in consumer credit, and when borrowers face a decision on whether to default on mortgage or non-mortgage loans first, banking relationship may matter. Our study provides first evidence into the interplay between banking relationship and consumer default priority via credit bureau data of 1 million individuals in Thailand. We find that same-bank borrowers are less likely to default on mortgage loans first, and borrowers with longer banking relationship and lower switching cost are more likely to default on mortgage loans first (which is welfare-improving). Our results suggest that banking relationship can lead to better outcomes for defaulting borrowers even when switching cost is high.

Banking Regulatory Constraints and Personal Bankruptcy Filings in the US

ABSTRACT The economic well-being of a household depends on its access to credit and also its access to a legal system for managing over-indebtedness. Our hypothesis is that the removal of regulatory constraints on a bank’s ability to expand in new geographic markets increases households’ access to credit, which in turn, contributes to a rise in consumer defaults. In the US, we find a net increase in Chapter 13 bankruptcies following a loosening of a state’s restrictions on multi-branch banking, compared to the increase in Chapter 13 bankruptcies in states that did not change their banking rules. The increased mortgage lending after branch deregulation helps explain this rise in Chapter 13 filings, suggesting that homeowners use the Chapter 13 code to save their houses. Further, the effects of the mortgage supply channel are greater in areas with low bank concentration. Overall, our findings are relevant to policymakers in their efforts to either set up a new personal insolvency regime or modify the existing bankruptcy process.

Mathematical justification on the origin of the sigmoid in logistic regression

Logistic regression is a commonly used classification algorithm in machine learning. It allows categorizing data into discrete classes by learning the relationship from a given set of labeled data. It learns a linear relationship from the given data set and then introduces nonlinearity through an activation function to determine a hyperplane that separates the learning points into two subclasses. In the case of logistic regression, the sigmoid is the most used activation function to perform binary classification. The choice of sigmoid for binary classifications is justified by its ability to transform any real number into a probability between 0 and 1. This study provides, through two different approaches, a rigorous mathematical answer to the crucial question that torments us, namely where does this logistic function on which most neural network algorithms are based come from? References Stoltzfus, "Logistic regression: A brief primer," Academic Emergency Medicine, vol. 18, no. 10, pp. 1099-1104, 2011. Peng et al, "An introduction to logistic regression analysis and reporting," The Journal of Educational Research, vol. 96, no. 1, pp. . Costa et al, "A logistic regression model for consumer default risk," Journal of Applied Statistics, vol. 47, no. 13-15, pp. 2879-2894, 2020. Gatzert and M. Schubert, "Cyber risk management in the us banking and insurance industry: A textual and empirical analysis of determinants and value," Journal of Risk and Insurance, vol. 89, no. 3, pp. 725-763, 2022. Premsmith and H. Ketmaneechairat, "A predictive model for heart disease detection using data mining techniques," Journal of Advances in Information Technology, vol. 12, pp. 14-20, 2021. Almotiri et al, "Using api with logistic regression model to predict hotel reservation cancellation by detecting the cancellation factors," International Journal of Advanced Computer Science and Applications, vol. 12 , no. 6 , pp. . Kudupudi et al, "Spam message detection using logistic regression," International Journal of Advanced Computer Science and Applications, vol. 9, no. 9, pp. 815-818, 2021. Keren and . Cuiwei, "Housing price analysis using linear regression and logistic regression: A comprehensive explanation using melbourne real estate data," in 2021 IEEE International Conference on Computing (ICOCO), 2021, pp. 241-246. Dheeru and G. Casey, "UCI machine learning repository," 2017. [Online]. Available: http://archive.ics. uci.edu/ml Goldbloom, "Kaggle dataset," 2010. [Online]. Available: https: //www.kaggle.com/ Febrianti et al, "The parameter estimation of logistic regression with maximum likelihood method and score function modification," Journal of Physics: Conference Series, vol. 1725, no. 1, p. 012014, 2021. Lucena, "Loss functions for classification using structured entropy," 2022. [Online]. Available: https://arxiv.org/abs/2206.07122 Hikmat and A. Abdulazeez, "Comparison of optimization techniques based on gradient descent algorithm: a review," PalArch?s Journal of Archaeology of Egypt/Egyptology, vol. 18, no. 4, pp. 2715-2743, 2021.E. Norton et al, “Odds ratios-current best practice and use,” Journal of the American Medical Association, vol. 320, no. 1, pp. 84–85, 2018 Tong, Fundamental Properties and Sampling Distributions of the Multivariate Normal Distribution. Springer New York, 1990, pp. 23– 61.

Incorporating multilevel macroeconomic variables into credit scoring for online consumer lending

• Multilevel macroeconomic variables (MVs) are first applied to credit scoring. • We emphasize the credit risk of online consumer lending in developing economies. • A structural model is developed to analyze the determinants of consumer credit risk. • A Bayesian MV selection and lag optimization approach is proposed. • The incorporation of multilevel MVs outperforms the benchmarks significantly. Booming online consumer lending encounters high credit risk and thus needs well-designed credit scoring models. As a supplementary data source, multilevel macroeconomic variables (MVs), which means mixed regions, data frequency, and lags of MVs, are combined with application data for credit scoring. Moreover, we propose a Bayesian MV selection and lag optimization method to handle the highly correlated MVs and capture flexible lag effects. A structural model for consumer default behavior is proposed to analyze the potential role of multilevel MVs in theoretically predicting default loans. Validated on a real-world dataset from an anonymous Chinese online consumer lending platform, the empirical results confirm that multilevel MVs are significant determinants of consumer credit risk. The comparison of classification performance further implies the superiority of incorporating multilevel MVs and the proposed MV selection and lag optimization method relative to benchmarks. Gradient boosting decision tree-based approaches provide significantly better performance than industry benchmarks while maintaining interpretability via Shapley additive explanations values.

Towards Achieving Long-Term Debt Sustainability: A Systematic Review of the Key Determinants of Personal Bankruptcy

Purpose: This systematic review aimed to assess previous research about financial and non-financial causes of personal bankruptcy among individual households. Additionally, the paper aimed to provide an insight into the key determinants of personal bankruptcy and to determine their relationship with individual characteristics. The fundamental causes of bankruptcy and its effects on financial status were also discussed. Through understanding the causes of bankruptcy, we hope to help financial institutions to minimise the number of personal bankruptcies.
 Design/methodology/approach: A comprehensive systematic search was conducted to identify articles on determinants of personal bankruptcy. The selected articles were then analysed using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) protocol.
 Findings: We identified several themes that emerged as the key determinants of personal bankruptcy filings. These determinants were demographic indicators, socioeconomic status indicators, debt indicators, financial indicators, social stigma indicators, behavioural indicators, and macroeconomic indicators.
 Research implications: The key determinants of personal bankruptcy that were identified in this systematic review are renowned factors in the personal bankruptcy literature. Therefore, these determinants should be studied extensively to examine their effects in other studies and using a different type of datasets.
 Practical implications: The findings of this study help the financial institutions to predict the likelihood of consumer default by developing an effective credit scoring model. Additionally, the development of an effective credit scoring model could serve as an early warning indicator to identify “high risk” client.
 Originality/value: Bankruptcy is a long-term process that does not occur instantly. Therefore, a longitudinal and comprehensive approach is required to understand bankruptcy. Our findings contribute to the current literature by providing a better understanding of the causes of personal bankruptcy. We recommend developing an effective credit scoring model to predict the likelihood of personal bankruptcy.

Consumer defaults and social capital

Using account level data from a credit bureau, we study the role that social capital plays in consumer default decisions. We find that borrowers in communities with greater social capital are significantly less likely to default on loans, even after adjusting for different levels of income and other characteristics such as credit scores. The results are strongest for potentially strategic defaults on mortgages; a one standard deviation increase in social capital reduces such defaults by 12.4 %. These results can be generalized to any mortgage default. Our results also indicate that the effect of social capital is most prominent among more creditworthy borrowers, suggesting that when given a choice, the social cost of defaulting is an important factor affecting default decisions. We find a similar impact of social capital on consumer defaults in other datasets with more detailed information on borrowers as well. Our results are robust to modeling and methodology choices, as well as controlling for other drivers of default such as wealth, income and amenities from homeownership. Our results suggest that increasing social capital via measures to build community cohesion such as promotion of owner-occupied home ownership may be one avenue to deter consumer default.

Does data protection legislation increase the quality of internet services?

Digital firms attract consumers and collect their data by offering service enhancements and data security. These require separate types of investment. In light of the GDPR, data collection now requires explicit consumer consent, i.e. opt-in. This changes the consumer default option and the data provision decision when consumers are loss averse. We examine the consequences for investment. We set out the conditions under which opt-in increases both types of investment and when security comes at the expense of service quality. We further find that most consumer types gain, even when service quality falls.

Placing Consumers at the Front of the Relief Effort: Redirecting Credit Card Interest Charges

Catastrophes including the COVID19 pandemic of 2019-2020 impose great financial stress on consumers. This op-ed proposes the distribution of economic relief directly to consumers by authorizing credit card issuers to bill Congress for portions of the interest that otherwise would be charged to cardholders. Significant benefits include expanding access to consumer credit when it otherwise would be expected to diminish, reduced consumer default rates and bank charge-offs, and greater stimulus to overall economic welfare.

FinTech Marketplace Lending, Default Risk, and the Business Cycle

This paper explores default in the FinTech marketplace lending market using a dataset of both extensive credit and soft information for borrowers from the largest marketplace lender in the United States. I find that both macro and regional economic conditions play a role in consumer default and should be taken into consideration when assessing credit risk. I show that lenders operating in this market increasingly focus on subprime borrowers, whose default rates are more sensitive to macro and regional economic conditions than those of prime borrowers. Based on estimates from a duration model, I provide counterfactual analyses of what default rates and the associated total losses would look like in different economic scenarios. In the case of a recession, the losses would be 37 percent higher than in the case of an expansion. For the same volume of loans in the recession, doubling the subprime share would lead to an additional 7.5 percent increase in losses.

On the Rise of FinTechs: Credit Scoring Using Digital Footprints

Abstract We analyze the information content of a digital footprint—that is, information that users leave online simply by accessing or registering on a Web site—for predicting consumer default. We show that even simple, easily accessible variables from a digital footprint match the information content of credit bureau scores. A digital footprint complements rather than substitutes for credit bureau information and affects access to credit and reduces default rates. We discuss the implications for financial intermediaries’ business models, access to credit for the unbanked, and the behavior of consumers, firms, and regulators in the digital sphere. (JEL G20, G21, G29)

Informational synergies in consumer credit

We investigate whether lenders can realize informational synergies by simultaneously obtaining private information from different accounts of the same borrower. Synergies exist if such information is complementary to each other. We focus on consumer credit, using 3.5 million observations from checking accounts and credit card accounts of the same individuals during 2007–2014. First, activity from both accounts is complementary for estimating consumer default beyond credit scores, borrower characteristics and relationship characteristics. Checking accounts display warning indications about consumer default earlier and more accurately than credit card accounts. Second, decision errors are lower when lenders consider cross-product information. The evidence suggests significant informational synergies that are important for the supply and allocation of credit.