Decision-Making Techniques for Credit Resource Management Using Machine Learning and Optimization

• Published in: Information (Basel) 2020-03, Vol.11 (3), p.144
• Main Author: Orlova, Ekaterina V.
• Format: Article
• Language: English
• Subjects: Banking industry; Banks; Control methods; Control theory; credit operations; credit policy decision-making; credit portfolio optimization; credit risk management; credit scoring; Decision making; Default; Financial management; Growth rate; Interest rates; International banking; International finance; Loans; Machine learning; New technology; Optimization; Portfolio management; Profitability; Regulation of financial institutions; Resource management; Statistical methods; Supervision; Systems analysis; Systems stability
• ISSN: 2078-2489; 2078-2489
• DOI: 10.3390/info11030144

Credit operations are fundamental in the banks’ activities and provide a significant share of their income. Under an increased demand for credit resources, credit risks are growth. It keeps the importance of the problem of an increase in the efficiency of lending management processes in financial institutions. The aim of the work is the justification and development of new technology and models for the management of bank lending that reduce credit risks and increases lending efficiency. The research materials are statistical data from the Bank of Russia and Rosstat. The methods of system analysis, methods of control theory, methods of statistics, optimization methods and machine learning are used. The positive results of the implementation of the proposed technology and credit management models are of practical importance to ensure the profitability growth of credit organization and contribute to its competitiveness.