A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Big Data Analytics for Credit Risk Prediction: Machine Learning TechniquesTechniques and Data Processing Approaches
Credit risk scoringCredit risk scoring approaches study and analyse customer’sCustomer financial records to provide the financial institutionsFinancial institution with a summarised decision making information. However, they still suffer from the lack of a solid Big Data solutions to recognise, model and predict credit risk data patternsPatterns. This chapter aims to propose machine learningMachine learning pipelines which are capable of extracting principal information from a huge and public credit risk dataset. For this, a Big data-enabled data preprocessing approach is proposed to prepare the given dataset. Moreover, two machine learningMachine learning models including Decision TreeDecision Tree and Gradient BoostingGradient boosting are trained, tested and evaluated to find the best-fittedBest-fitted techniquesTechniques for credit risk predictionCredit risk prediction. According to the results, Gradient BoostingGradient boosting (AUC of 0.987) givesAUC a better performance as compared toDecision Tree Decision TreeAUC (AUC of 0.488).
Big Data Analytics for Credit Risk Prediction: Machine Learning TechniquesTechniques and Data Processing Approaches
Credit risk scoringCredit risk scoring approaches study and analyse customer’sCustomer financial records to provide the financial institutionsFinancial institution with a summarised decision making information. However, they still suffer from the lack of a solid Big Data solutions to recognise, model and predict credit risk data patternsPatterns. This chapter aims to propose machine learningMachine learning pipelines which are capable of extracting principal information from a huge and public credit risk dataset. For this, a Big data-enabled data preprocessing approach is proposed to prepare the given dataset. Moreover, two machine learningMachine learning models including Decision TreeDecision Tree and Gradient BoostingGradient boosting are trained, tested and evaluated to find the best-fittedBest-fitted techniquesTechniques for credit risk predictionCredit risk prediction. According to the results, Gradient BoostingGradient boosting (AUC of 0.987) givesAUC a better performance as compared toDecision Tree Decision TreeAUC (AUC of 0.488).
Big Data Analytics for Credit Risk Prediction: Machine Learning TechniquesTechniques and Data Processing Approaches
Urban Sustainability
Pourroostaei Ardakani, Saeid (author) / Cheshmehzangi, Ali (author)
2023-09-28
12 pages
Article/Chapter (Book)
Electronic Resource
English