The Norms of Algorithmic Credit Scoring

Aggarwal, Nikita

doi:10.1017/s0008197321000015

Cited by 32 publications

(12 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This evolution has been characterized by a transition from simplistic, rule-based algorithms to more sophisticated, data-driven approaches that harness the power of predictive analytics and machine learning algorithms. By leveraging a broader array of variables and incorporating advanced statistical techniques, modern credit scoring models aim to provide a more comprehensive assessment of an individual's creditworthiness, thereby facilitating more informed lending decisions (Aggarwal, 2021).…”

Section: The Evolution Of Credit Scoring Modelsmentioning

confidence: 99%

Evaluating the fairness of credit scoring models: A literature review on mortgage accessibility for under-reserved populations

Taiwo Inumidun Adegoke,

Onyeka Chrisanctus Ofodile,

Nneka Adaobi Ochuba

et al. 2024

GSC Adv. Res. Rev.

View full text Add to dashboard Cite

This literature review critically evaluates the fairness of credit scoring models concerning mortgage accessibility for under-reserved populations. The review scrutinizes a diverse range of scholarly articles, reports, and empirical studies spanning various disciplines, including finance, economics, sociology, and public policy. It examines the methodologies, findings, and limitations of existing research to illuminate the multifaceted dimensions of credit scoring fairness and its implications for mortgage accessibility. Firstly, the review outlines the conceptual framework of credit scoring fairness, emphasizing the importance of equality, transparency, and accountability in credit assessment processes. It explores the evolution of credit scoring models and their impact on mortgage lending practices, particularly for historically marginalized communities such as racial minorities, low-income households, and individuals with limited credit histories. Secondly, the review analyzes the methodologies employed in evaluating the fairness of credit scoring models. It identifies key metrics and statistical techniques used to assess disparities in mortgage approval rates, interest rates, and loan terms across demographic groups. Thirdly, the review synthesizes empirical evidence on the extent and persistence of disparities in mortgage accessibility for under-reserved populations. It highlights systemic barriers, including discriminatory lending practices, redlining, and institutionalized biases embedded within credit scoring models. Fourthly, the review discusses the implications of credit scoring fairness for financial inclusion, social equity, and economic mobility. It underscores the need for innovative policy interventions, industry best practices, and consumer education initiatives to address systemic inequities in mortgage lending and promote inclusive homeownership opportunities for under-reserved, Finally, this literature review offers a comprehensive overview of the fairness of credit scoring models in the context of mortgage accessibility for under-reserved populations. By synthesizing empirical evidence, theoretical frameworks, and policy implications, it contributes to a deeper understanding of the challenges and opportunities in promoting equitable access to homeownership and financial security for all.

show abstract

Section: The Evolution Of Credit Scoring Modelsmentioning

confidence: 99%

Evaluating the fairness of credit scoring models: A literature review on mortgage accessibility for under-reserved populations

Taiwo Inumidun Adegoke,

Onyeka Chrisanctus Ofodile,

Nneka Adaobi Ochuba

et al. 2024

GSC Adv. Res. Rev.

View full text Add to dashboard Cite

show abstract

“…As an example of the potential trade-off, platforms providing access to previously underserved consumers (eg consumers with "thin files" in a credit scoring context) may depend on more personal data or a wider variety of data from individuals in order to provide a service viably (eg to price credit risk accurately). However, inadequate coordination between existing regulatory frameworks in many jurisdictions -particularly data protection and financial regulation -means that there are unsatisfactory mechanisms in place for navigating these normative trade-offs (Aggarwal, 2021).…”

Section: Apply Existing Financial Regulation Competition and Data Pri...mentioning

confidence: 99%

Role of UPI Application Usage and Mitigation of Payment Transaction Frauds: An Empirical Study

Edburg,

Umadevi,

Vidya

et al. 2024

MBR

View full text Add to dashboard Cite

The objective of this investigation is to analyze the intention behind user behavior toward employing Unified Payment Interface (UPI) apps and pinpointing successful solutions for mitigating frauds linked to them. This will increase safety measures, which would lead to an escalation in usage among consumers, ultimately resulting in higher financial inclusion across India through cashless transactions. The Indian digital payment system has been transformed by these platforms, including Google Pay, PhonePe, and Paytm, which together account for over 90% of all online payments made. Users are attracted primarily due to its convenience as well as ease-of-use factors along with influence from their peers who have turned into avid users themselves. Largely, due to COVID-19 lockdown disruptions many people shifted away from traditional monetary exchanges toward Internet Banking options leading to a surge-related crime involving transactional fraudulent practices costing up to 346%. The popularity itself throughout time due again mainly because it’s easy access capabilities UPI payment app development on fraudulent activities continued. A structured questionnaire was adopted during the collection phase within Chennai City among active UPI payment apps users whose data were analyzed using multivariate statistical techniques. The result proves that predictors such as perceived security, safety, risk consistent advantageous represents key inferences, supplying impetus towards utilizing technology and providing cautionary advice where deficiencies subsist. Info dissemination, emphasizing feature/benefit analysis targeting core customer groups, delivered periodically supplemented defensive protocols, incorporating trial process adaptations can mitigate further risk associated with application utilization. Reader response, demonstrating accommodative response based on familiarity, empowering generational social structure, and enabling transformation gained momentum, demonstrates structural readjustment and solidifies the benefits borne out by increased adaption ratified effective outcomes accruing overall benefits, favourably impacting a variety of demographic profiles, and guaranteeing continued use.

show abstract

“…Many borrowers in emerging markets where ICS is most prevalent 4 lack both formal credit histories and access to traditional credit bureaus. In Indonesia, credit bureaus reach only 20-25% of the population (Aggarwal, 2021). This makes alternative data sources crucial for credit assessment.…”

Section: The Power Of Data In Credit Scoringmentioning

confidence: 99%

International Experiences with Innovative Credit Scoring: Lessons for Indonesia

Wijaya,

Nidhal

2023

View full text Add to dashboard Cite

The Norms of Algorithmic Credit Scoring

Cited by 32 publications

References 27 publications

Evaluating the fairness of credit scoring models: A literature review on mortgage accessibility for under-reserved populations

Evaluating the fairness of credit scoring models: A literature review on mortgage accessibility for under-reserved populations

Role of UPI Application Usage and Mitigation of Payment Transaction Frauds: An Empirical Study

International Experiences with Innovative Credit Scoring: Lessons for Indonesia

Contact Info

Product

Resources

About