Managerial Finance · 1992 · 191 citations · 1 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningStatistical LearningCredit AnalysisCredit RiskCredit ScoringDeep LearningNeural NetworksPattern RecognitionArtificial Neural Network ScoringBorrower Credit ScoringCredit Score ModelingHoldout Sample EvaluationInput-output NetworksMachine Learning Credit ScoringNeural Network ClassificationPayment
Abstract Neural networks offer an alternative to numerical scoring schemes for credit granting and extension decisions. A standard back‐ propagation neural network running on a DOS personal computer is used with 125 credit applicants whose loan outcomes are known. Applicant characteristics are described as input neurons receiving values representing the individuals' demographic and credit information. Three categories of payment history, delinquent, charged‐off, and paid‐off, are used as the networks output neurons to depict the loan outcomes. After training on part of the data, correct classifications were made on 76–80% of the holdout sample.
1