Файл	Ном	Сабт карда шуд
Nizamitdinov Akhlitdin Ilyositdinovich	CREDIT SCORING MODELS BASED ON MACHINE LEARNING ALGORITHMS	56

Authors: Nizamitdinov Akhlitdin Ilyositdinovich - Doctor of Philosophy (PhD), The Senior Teacher of the Digital Economy Department at KPITTU

JOURNAL NUMBER: 3(58). YEAR OF ISSUE: 2021. LANGUAGE OF THE ARTICLE: Russian

ANNOTATION

Lending has played an important role in the financial world for recent years. This type of financial activity has become popular in the financial sector of the Republic of Tajikistan in the last decade. The article discusses methods for constructing credit scoring models in world practice. Experts and researchers in this field primarily assign numerical scores to people, known as credit scores, to measure the risk and their creditworthiness. Although this type of financial activity is quite profitable, it carries a large risk, which in the field of loan lending is called credit risk.

Therefore, forecasting a client's credit default is the most important aspect in the financial activities of organizations. In recent years, machine learning algorithms have become frequently used in credit default classification problems. Such algorithms are logistic regression, k-nearest neighbors (KNN), decision tree, random forest, etc.

KEY WORDS

lending, credit scoring, default risk, machine learning algorithms, logistic regression, decision tree

• Prev
• Next