KREDIT XAVFINI BAHOLASH UCHUN ML-MODEL YARATISH.
Keywords:
Kredit xavfi ,Kredit riskini baholash, Machine Learning, Logistic Regression, Random Forest, Gradient Boosting, Mijoz tahlili, Moliyaviy ko‘rsatkichlar.Abstract
Ushbu loyiha kredit oluvchilarning moliyaviy xatti-harakatlarini tahlil qilib, kreditni qaytarmaslik xavfini oldindan baholashga qaratilgan. Ma’lumotlar to‘plami asosida kredit tarixining ishonchliligi, daromad, yoshi, ish staji va boshqa ko‘rsatkichlar o‘rganildi. Machine Learning modellari, jumladan Logistic Regression, Random Forest va Gradient Boosting algoritmlari qo‘llanib, mijozning kreditni qaytarmaslik ehtimoli hisoblandi. Model aniqligi, ROC-AUC va Confusion Matrix kabi metrikalar orqali baholandi. Ushbu tizim banklar va moliya tashkilotlariga qaror qabul qilish jarayonini avtomatlashtirishda hamda xavf darajasini kamaytirishda yordam beradi.
References
1. James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An Introduction to Statistical Learning with Applications in R. Springer.
2. Géron, A. (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow. O’Reilly Media.
3. Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer.
4. Brownlee, J. (2016). Machine Learning Mastery: Practical Machine Learning Tutorials. Machine Learning Mastery.
5. Provost, F., & Fawcett, T. (2013). Data Science for Business: What You Need to Know about Data Mining and Data-Analytic Thinking. O’Reilly Media.
6. Scikit-learn official documentation: https://scikit-learn.org
7. World Bank. (2020). Credit Risk Assessment and Management in Banking.
