Abstract

Credit risk as the board in banks basically centers around deciding the probability of a customer's default or credit decay and how expensive it will end up being assuming it happens. It is important to consider major factors and predict beforehand the probability of consumers defaulting given their conditions. Which is where a machine learning model comes in handy and allows the banks and major financial institutions to predict whether the customer, they are giving the loan to, will default or not. This project builds a machine learning model with the best accuracy possible using python. First we load and view the dataset. The dataset has a combination of both mathematical and non-mathematical elements, that it contains values from various reaches, in addition to that it contains a few missing passages. We preprocess the dataset to guarantee the AI model we pick can make great expectations. After the information is looking great, some exploratory information examination is done to assemble our instincts. Finally, we will build a machine learning model that can predict if an individual's application for a credit card will be accepted. Using various tools and techniques we then try to improve the accuracy of the model. This project uses Jupyter notebook for python programming to build the machine learning model. Using Data Analysis and Machine Learning, we attempted to determine the most essential parameters for obtaining credit card acceptance in this project. The machine learning model we built gave an 86 % accuracy for predicting whether the credit card will be approved or not, considering the various factors mentioned in the application of the credit card holder. Even though we achieved an accuracy of 86%, we conducted a grid search to see if we could increase the performance even further. However, using both the machine learning models: random forest and logistic regression, the best we could get from this data was 86 percent.

Highlights

  • Credit hazard the board in banks centers around deciding whether the customer will default or her credit will break down

  • Prior default has a major impact on the decision of credit card request approval

  • When we look into the number of approval from both the classes it's 7% and 78.7% from their respective totals. This indicates if the applicant has no prior defaults, probability of getting the credit card request approved is much higher

Read more

Summary

INTRODUCTION

Credit hazard the board in banks centers around deciding whether the customer will default or her credit will break down. Since the low compensation of youth, customers started defaulting on their portions and by February 2006, obligation because of Mastercards and other money cards was around 260 billion USD. This led to numerous issues in Taiwan. Banks presently utilize numerous order strategies like nave bayes and KNN to investigate hazard forecast. FICO rating cards are a typical danger control strategy in the monetary business which utilize individual data of the clients and information presented by them to foresee the likelihood of future defaults and Mastercard borrowings.

Conceptual Overview
Logistic Regression
Hyperparameters:
Inspecting the applications
Handling the missing values
Pre-processing the data
Tools to make the model perform better
RESULTS AND ANALYSIS
CONCLUSION

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.