Affiliations: Department of Computer Engineering, Sardar Patel Institute of Technology, Mumbai, India
Correspondence:
[*]
Corresponding author. Swati V. Kulkarni, Department of Computer Engineering, Sardar Patel Institute of
Technology, Mumbai, India. E-mail: [email protected].
Abstract: The Credit Score is the most fascinating three digit number associated with an individual or an organization as it figures out what loans you will qualify for and the interest rate you will pay. Current credit scoring system is based on the financial history of individual or organization. This work illustrates a new credit scoring system which incorporates Legacy credit score and emotional/social credit score. The legacy credit score is based on the financial history of an individual. The emotional/social credit score is based on analysis and study of social media and other web interaction. The new system called information trustworthiness is developed to improve the precision of social media data when compared with data from reliable sources. Finally, the proper fractions of legacy credit score and emotional/social credit score are added to get Advanced Credit Score. This score is more precise than Legacy credit score as it also incorporates personality traits of an individual which have a high impact on one’s financial behavior. However, the accuracy of the Advanced Credit Score is dependent on the fractions of legacy credit score and emotional/social credit score selected. The advance scoring system can be effectively used to distinguish people who defaulted many times and who never used loans or services like credit cards which are otherwise not possible using legacy financial credit scoring system.
Keywords: Credit score, Naive Bayes, CRISP-DM, data mining, Multilayer
Perceptron, Random Forest, Random Tree
