Home / Current Issue / Paper 1706648
Efficient Analysis of Financial Risks Using Multinomial Logistic Regression
Subject area: Science,Engineering and Technology · Area of research: Machine Learning, Big Data
Abstract
Banks are a basic part of financial development. The banking industry has credit risk like different businesses in the finance division. Predicting credit risk is the biggest problem for the financial area in most countries around the world. Credit risk prediction and loan lending process are difficult for credit managers. This research work is focused on making a prediction model using machine learning techniques. The credit risk prediction model will change the high impact of the ?nancial industry. The primary motivation behind this paper is to analyze the relative execution between tuned Multinomial Logistic Regression and Multinomial logistic regression fashions for default classi?cation and credit score chance assessment. The ?nancial information from a dataset of 30000 records in the UCI repository for prediction as default markers. The research goal is to find credit risk probabilities are assessed by some classifier metrics. It is shown that Multinomial Logistic Regression (MLR) significantly outperforms than other Classifier models, especially under the state of credit risk prediction model will change the high impact of the ?nancial industry.
Keywords
Machine Learning, Logistic Regression, Credit Risk, Classifier Matrics
How to cite this paper
@article{1706648,
author = {Dr. G. Arutjothi, Dr. C. Senthamarai},
title = {Efficient Analysis of Financial Risks Using Multinomial Logistic Regression},
journal = {Iconic Research And Engineering Journals},
year = {2024},
volume = {8},
number = {6},
pages = {893-898},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1706648.pdf},
abstract = {Banks are a basic part of financial development. The banking industry has credit risk like different businesses in the finance division. Predicting credit risk is the biggest problem for the financial area in most countries around the world. Credit risk prediction and loan lending process are difficult for credit managers. This research work is focused on making a prediction model using machine learning techniques. The credit risk prediction model will change the high impact of the ?nancial industry. The primary motivation behind this paper is to analyze the relative execution between tuned Multinomial Logistic Regression and Multinomial logistic regression fashions for default classi?cation and credit score chance assessment. The ?nancial information from a dataset of 30000 records in the UCI repository for prediction as default markers. The research goal is to find credit risk probabilities are assessed by some classifier metrics. It is shown that Multinomial Logistic Regression (MLR) significantly outperforms than other Classifier models, especially under the state of credit risk prediction model will change the high impact of the ?nancial industry.},
keywords = {Machine Learning, Logistic Regression, Credit Risk, Classifier Matrics},
month = {December},
}