Deep Learning for Repayment Prediction in Leasing Companies

Purpose: This paper aims to improve repayment prediction in leasing companies using a deep learning model. Design/Methodology/Approach: In this work, we prepare some models and compare them with other solutions based on artificial intelligence like, multiple regression, decision tree, random forest, bagging classifier. Findings: The developed model enables automatic analysis of large amounts data that changes quickly is often unstructured. Additionally, the input vectors consist specific attributes related leasing. results experiments allow us conclude accuracy higher than reference used currently companies. Practical Implications: has recently been implemented Decision Engine system (a by Poland) BI Technologies Sp. Z o.o. Company. Originality/Value: Financial institutions automate simplify credit procedures, eliminating analyst from process replacing him decision-making processes scoring or similar models. However, automatically analyze significance phenomena occurring environment organizations affect assessment customer's repayments, it necessary use tools.