ISSUES IN THE DESIGN AND IMPLEMENTATION OF CREDIT SCORING SYSTEMS

1980 ◽  
Vol 15 (4) ◽  
pp. 17-17 ◽  
Author(s):  
Gary G. Chandler ◽  
John Y. Coffman
Author(s):  
Roman Z. Rouvinsky ◽  
Alexey A. Tarasov

This article is dedicated to identification and examination of doctrinal grounds and historical prerequisites of the" Social Credit System (trustworthiness)” – a project introduced in the People’s Republic of China in the early 2000s, and currently being “exported” from People’s Republic of China to other countries. In the course of this research, the author analyzed the specific Chinese sources and prerequisites for the creation of modern social rating and control system, as well as non-national sources mostly attributed to the history of Western European political legal thought and Western social institutions. Viewing "Social Credit System" as a technique for exercising social control and oversight, the authors discover its origins in J. Bentham’s project" Panopticon ", Taylor’s philosophy of management, Confucian and legalistic traditions of Imperial China, ideas and institutions of the era of Chinese cultural revolution, as well as U.S. credit scoring systems. This article is the first within Russian science to study the historical and doctrinal prerequisites of China’s "Social Credit System”, taking into account the works of foreign scholars dedicated to the history of its establishment.  A new perspective is given on the Confucian ideas the ideas of Fajia (Legalism) School, which are interpreted as complementary sources of the modern system of social control developed in PRC. The authors believe that China’s “Social Credit System” and the related techniques of control represent a so-called “bridge” that connects “Western” history of the development of social institutions with typically “Eastern” political and sociocultural tradition. In conclusion, attention is turned to the positive aspects, as well as “shadow” side of implementation of the mechanism of “Social Credit System”, “reverse” of this process and all accompanying problems thereof.


Author(s):  
Nan Hu ◽  
Haojie Cheng

As the aim of large banks has been changing to select customers of highest benefits, it is important for banks to know not only if but also when a customer will default. Survival analyses have been used to estimate over time risk of default or early payoff, two major risks for banks. The major benefit of this method is that it can easily handle censoring and competing risks. An ROC curve, as a statistical tool, was applied to evaluate credit scoring systems. Traditional ROC analyses allow banks to evaluate if a credit-scoring system can correctly classify customers based on their cross-sectional default status, but will fail when assessing a credit-scoring system at a series of future time points, especially when there are censorings or competing risks. The time-dependent ROC analysis was introduced by Hu and Zhou to evaluate credit-scoring systems in a time-varying fashion and it allows us to assess credit scoring systems for predicting default by any time within study periods.


2009 ◽  
Vol 10 (3) ◽  
pp. 233-240 ◽  
Author(s):  
Huseyin Ince ◽  
Bora Aktan

Credit scoring is a very important task for lenders to evaluate the loan applications they receive from consumers as well as for insurance companies, which use scoring systems today to evaluate new policyholders and the risks these prospective customers might present to the insurer. Credit scoring systems are used to model the potential risk of loan applications, which have the advantage of being able to handle a large volume of credit applications quickly with minimal labour, thus reducing operating costs, and they may be an effective substitute for the use of judgment among inexperienced loan officers, thus helping to control bad debt losses. This study explores the performance of credit scoring models using traditional and artificial intelligence approaches: discriminant analysis, logistic regression, neural networks and classification and regression trees. Experimental studies using real world data sets have demonstrated that the classification and regression trees and neural networks outperform the traditional credit scoring models in terms of predictive accuracy and type II errors.


2017 ◽  
Vol 7 (5) ◽  
pp. 2073-2082 ◽  
Author(s):  
A. G. Armaki ◽  
M. F. Fallah ◽  
M. Alborzi ◽  
A. Mohammadzadeh

Financial institutions are exposed to credit risk due to issuance of consumer loans. Thus, developing reliable credit scoring systems is very crucial for them. Since, machine learning techniques have demonstrated their applicability and merit, they have been extensively used in credit scoring literature. Recent studies concentrating on hybrid models through merging various machine learning algorithms have revealed compelling results. There are two types of hybridization methods namely traditional and ensemble methods. This study combines both of them and comes up with a hybrid meta-learner model. The structure of the model is based on the traditional hybrid model of ‘classification + clustering’ in which the stacking ensemble method is employed in the classification part. Moreover, this paper compares several versions of the proposed hybrid model by using various combinations of classification and clustering algorithms. Hence, it helps us to identify which hybrid model can achieve the best performance for credit scoring purposes. Using four real-life credit datasets, the experimental results show that the model of (KNN-NN-SVMPSO)-(DL)-(DBSCAN) delivers the highest prediction accuracy and the lowest error rates.


2020 ◽  
Vol 89 (4) ◽  
pp. 73-88
Author(s):  
Pauline Affeldt ◽  
Ulrich Krüger

Summary: The global trend toward cashless payment started well before the corona pandemic. Along with it, investors in the data-driven tech industry are inspired by the promise of targeted behavioral scoring based on big data. It seems economically tempting to combine these two trends by using all data generated by the payment services to create personal profiles. However, this business model conflicts with the individual’s right of informational self-determination and raises questions regarding inaccuracies, discrimination, and the non-transparency of the algorithms underlying these profiles. Our article provides a short overview over the recent economic developments in the financial service industry and a legal assessment in light of the GDPR. Not everything that is feasible with big data scoring using alternative payment data is legally allowed in Europe. Nevertheless, traditional banks could have the opportunity to improve their internal credit scoring systems and use individual customer profiles to further market their financial services. Zusammenfassung: Nicht erst seit der Corona Pandemie gibt es weltweit den Trend zum bargeldlosen Zahlungsverkehr. Zudem beflügelt die Vorstellung eines zielgenauen Behavioral (Big Data) Scoring die Fantasien von Investoren in der Datentechnologiebranche. Es scheint ökonomisch verführerisch, beide Trends zusammenführen, wenn man alle Daten aus dem Zahlungsverkehr für ein persönliches Profil auswerten würde. Dieses Geschäftsmodell liegt jedoch mit dem Recht des Einzelnen auf informationelle Selbstbestimmung im Konflikt und wirft Fragen auf im Hinblick auf Ungenauigkeit, Diskriminierung und Intransparenz. Unser Artikel gibt einen Überblick über die ökonomische Entwicklung des Sektors und eine rechtliche Bewertung insbesondere aus Sicht der europäischen Datenschutz-Grundverordnung. Nicht alles was im Big Data Scoring mit alternativen Zahlungsdaten möglich sein könnte, ist in Europa auch rechtlich zulässig. Vor allem für die „klassischen“ Banken könnte sich gleichwohl eine Möglichkeit eröffnen ihre internen Credit Scoring Systeme zu verbessern und mit angepasst-individuellen Kundenprofilen weitere ihrer Finanzdienstleistungen zu vertreiben.


Author(s):  
Lara Marie Demajo ◽  
Vince Vella ◽  
Alexiei Dingli

With the recent boosted enthusiasm in Artificial Intelligence (AI) and Financial Technology (FinTech), applications such as credit scoring have gained substantial academic interest. However, despite the evergrowing achievements, the biggest obstacle in most AI systems is their lack of interpretability. This deficiency of transparency limits their application in different domains including credit scoring. Credit scoring systems help financial experts make better decisions regarding whether or not to accept a loan application so that loans with a high probability of default are not accepted. Apart from the noisy and highly imbalanced data challenges faced by such credit scoring models, recent regulations such as the `right to explanation' introduced by the General Data Protection Regulation (GDPR) and the Equal Credit Opportunity Act (ECOA) have added the need for model interpretability to ensure that algorithmic decisions are understandable and coherent. A recently introduced concept is eXplainable AI (XAI), which focuses on making black-box models more interpretable. In this work, we present a credit scoring model that is both accurate and interpretable. For classification, state-of-the-art performance on the Home Equity Line of Credit (HELOC) and Lending Club (LC) Datasets is achieved using the Extreme Gradient Boosting (XGBoost) model. The model is then further enhanced with a 360-degree explanation framework, which provides different explanations (i.e. global, local feature-based and local instance- based) that are required by different people in different situations. Evaluation through the use of functionally-grounded, application-grounded and human-grounded analysis shows that the explanations provided are simple and consistent as well as correct, effective, easy to understand, sufficiently detailed and trustworthy.


2021 ◽  
Author(s):  
◽  
Simon Russell Copland

<p>Credit scoring is an automated exercise in predictive analytics deployed by retail lenders and their agents to overcome the perennial problem of the ‘information asymmetries’ existing between debtors and creditors. Credit scoring systematically outperforms ‘subjective’ decision-making by lenders about loan applications, lowering costs and increasing profitability by boosting the speed and consistency of judgements able to be made about credit risk. This system of expert knowledge has emerged as a crucial part of the lending infrastructure and a new ‘core competency’ for lenders. The implications for social subjecthood, however, are underexplored: the extant literature on finance and society says little about credit scoring’s effects as a ‘disciplinary device’ on credit consumers, or how scoring systems might accustom would-be borrowers to conduct and conceive of their lives in particular ways.  My thesis presents findings from an exploratory sociological study of consumer credit scoring systems in New Zealand. It analyses data gathered in 2013 from seventy women and men in focus groups and open-ended individual interviews about their subjective experiences of debt and credit scoring practices. The research fills a gap in critical social inquiry into consumer credit provision by using an interpretive qualitative approach to identify ways in which the commoditised information platforms administered by credit bureaus in New Zealand are involved in the self-understandings of individuals. The study draws on Marxist, Foucaultian and feminist understandings of finance and the consumer-subject to offer a critical reading of participants’ involvement in the workings of the credit economy. I suggest that the systematic surveillance of borrowers by lending institutions through credit bureaus not only implies new forms of economic control and population management, but extends the instrumental rationality of finance into the realm of society and the self. Credit scoring – a market device that operates as an “objective” site of reality construction and revalorisation of productive and exchange relations – hails us as dutiful consumers and citizens from the spaces and rhythms of financial activity. There is also evidence that it operates as a ‘technology of self’, permitting forms of self-administration whereby individuals constitute themselves as particular types of financially viable beings within the wider interpersonal and intersubjective complex of memories, measures, morals, corporeality, obligation, anxiety, and affect.  In this ‘techno-social’ production of the subject, in which credit agencies exist as loci or conduits of governmental intent, individuals located within borrowing collectives can be interpreted variously as: (a) credit subjects, consumers subjectified in service to the debt economy; (b) credit-scoring subjects, hyper-rationalised subjectivating complements to calculative market devices; and (c) creditworthy subjects, cultural obligors forming part of an unruly social unity concerned intersubjectively with emotive and intimate relations with families, co-dependants, employers, colleagues, retailers, credit grantors and institutions. The complex, multifaceted and sometimes contradictory ways in which participants negotiate new knowledges of themselves as sources of profit and governable risks call into question the adequacy of orthodox microeconomic accounts of ‘self-interested’ financial behaviour as a model for economic and social behaviour. They also emphasise how an overly simplistic reliance on the notion of ‘responsibilisation’ in the financialisation of everyday life is evident within some conceptions and critiques of the neoliberal subject. Participants’ experiences and self-understandings, rather, illustrate how the contemporary credit consumer is not simply dominated from above by the structural disciplines of finance capital, but is constituted ascendantly by harnessing individuals’ own capabilities of self-direction and expressions of freedom and desire. What is at stake in the unspoken politics of consumer finance is the targeting of the willing self as the raw material of credit – of the deeper affinities of finance with the discerning and reflexive subject.</p>


Sign in / Sign up

Export Citation Format

Share Document