awesome-credit-modeling

In the last years, the application of artificial intelligence methods on credit risk assessment has meant an improvement over classic methods. Recent works show that ensembles of classifiers achieve the better results for this kind of tasks.

The aim of this paper is to summarize the most recent developments in the application of evolutionary algorithms to credit scoring by means of a thorough review of scientific articles published during the period 2000–2012.

Surveys the techniques used — both statistical and operational research based — to help organisations decide whether or not to grant credit to consumers. It also discusses the need to incorporate economic conditions into the scoring systems and the way the systems could change from estimating the probability of a consumer defaulting to estimating the profit a consumer will bring to the lending organisation.

There have been several advancements in scorecard development, including novel learning methods, performance measures and techniques to reliably compare different classifiers, which the credit scoring literature does not reflect. This paper compares several novel classification algorithms to the state-of-the-art in credit scoring. In addition, the extent to which the assessment of alternative scorecards differs across established and novel indicators of predictive accuracy is examined.

The need for controlling and effectively managing credit risk has led financial institutions to excel in improving techniques designed for this purpose, resulting in the development of various quantitative models by financial institutions and consulting companies. Hence, the growing number of academic studies about credit scoring shows a variety of classification methods applied to discriminate good and bad borrowers. This paper aims to present a systematic literature review relating theory and application of binary classification techniques for credit scoring financial analysis. The general results show the use and importance of the main techniques for credit rating, as well as some of the scientific paradigm changes throughout the years.

A great many tools have been developed for supervised classification, ranging from early methods such as linear discriminant analysis through to modern developments such as neural networks and support vector machines. A large number of comparative studies have been conducted in attempts to establish the relative superiority of these methods. This paper argues that these comparisons often fail to take into account important aspects of real problems, so that the apparent superiority of more sophisticated methods may be something of an illusion. In particular, simple methods typically yield performance almost as good as more sophisticated methods, to the extent that the difference in performance may be swamped by other sources of uncertainty that generally are not considered in the classical supervised classification paradigm.

In credit scoring, feature selection aims at removing irrelevant data to improve the performance and interpretability of the scorecard. Standard techniques treat feature selection as a single-objective task and rely on statistical criteria such as correlation. Recent studies suggest that using profit-based indicators may improve the quality of scoring models for businesses.

An effective classificatory model in credit scoring will objectively help managers who rely on intuitive experience. This study proposes four approaches using the SVM (support vector machine) classifier for feature selection that retain sufficient information for classification purposes.

The features used may have an important effect on the performance of credit scoring models. The process of choosing the best set of features for credit scoring models is usually unsystematic and dominated by somewhat arbitrary trial. This paper presents an empirical study of four machine learning feature selection methods.

Section 2227 of the Economic Growth and Regulatory Paperwork Reduction Act of 1996 requires that, every five years, the Board of Governors of the Federal Reserve System submit a report to the Congress detailing the extent of small business lending by all creditors. The most recent one is dated September, 2017.

The prediction of corporate bankruptcies is an important and widely studied topic since it can have significant impact on bank lending decisions and profitability. This work reviews the topic of bankruptcy prediction, with emphasis on neural-network (NN) models and develops an NN bankruptcy prediction model, proposing novel indicators for the NN system.

An important ingredient to accomplish the goal of a more efficient use of resources through risk modeling is to find accurate predictors of individual risk in the credit portfolios of institutions. In this context the authors make a comparative analysis of different statistical and machine learning modeling methods of classification on a mortgage loan dataset with the motivation to understand their limitations and potential.

Finds that small business credit scoring is associated with expanded quantities, higher averages prices, and greater average risk levels for small business credits under $100,000, after controlling for bank size and other differences across banks.

Current work in downgrade risk modeling depends on multiple variations of quantitative measures provided by third-party rating agencies and risk management consultancy companies. There has been a wide push into using alternative sources of data, such as financial news, earnings call transcripts, or social media content, to possibly gain a competitive edge in the industry. This paper proposes a predictive downgrade model using solely news data represented by neural network embeddings.

Extends the existing literature on empirical research in the field of credit risk default for Small Medium Enterprizes (SMEs), proposing a non-parametric approach based on Random Survival Forests (RSF) and comparing its performance with a standard logit model.

Reviews the development of credit scoring (the way of assessing risk in consumer finance) and what is meant by a credit score. Outlines 10 challenges for Operational Research to support modelling in consumer finance.

This Working Paper by the Bank of International Settlements, while not as focused on credit risk, maps the conditions for and niches occupied by alternative credit, be it provided by fintechs or big tech companies.

Examines how statistical credit-scoring technologies became applied by lenders to the problem of controlling levels of default within American consumer credit. Explores their perceived methodological, procedural and temporal risks.

James (formerly CrowdProcess) is a now-defunct online credit risk management startup that provided risk management tools to financial institutions. This whitepaper offers an overview of machine learning applications in the field of credit risk modeling.

Reviews 130 journal papers from the period between 1995 and 2010, focusing on the development of state-of-the-art machine-learning techniques for bankruptcy prediction and credit score modeling. Also presents their current achievements and limitations.

Classic introduction and review of the subject of credit scoring.

Proposes an explainable AI model that can be used in credit risk management and, in particular, in measuring the risks that arise when credit is borrowed employing credit scoring platforms.

This Staff Working Paper from the Bank of England proposes a framework for addressing the ‘black box’ problem present in some Machine Learning (ML) applications.

The arrival of Big Data strategies is threatening the latest trends in financial regulation related to the simplification of models and the enhancement of the comparability of approaches chosen by financial institutions. Indeed, the intrinsic dynamic philosophy of Big Data strategies is almost incompatible with the current legal and regulatory framework as illustrated in this paper. Besides, the model selection may also evolve dynamically forcing both practitioners and regulators to develop libraries of models, strategies allowing to switch from one to the other as well as supervising approaches allowing financial institutions to innovate in a risk mitigated environment.

Discusses the traditional sampling conventions in credit modeling and argues that using larger samples provides a significant increase in accuracy across algorithms.

In-depth discussion.

Good introduction and discussion on the topic.

Peer-to-Peer lending platforms may lead to cost reduction, and to an improved user experience. These improvements may come at the price of inaccurate credit risk measurements. The authors propose to augment traditional credit scoring methods with “alternative data” that consist of centrality measures derived from similarity networks among borrowers, deduced from their financial ratios.