Loan predictive analysis and credit card fraud detection using Artificial neural networks
Prof. Bharat S. Dhak
, Ms. Trisha K. Sinha , Ms. Mansi Bhojraj Patiye , Ms. Pooja Arun Halbe , Ms. Sakshi Narendra Atram
Bank marketing prediction, neural networks, machine learning, visualization, neuron mathematical model, single neuron model math, Ann training process, Credit fraud Detection
In this project, we have built a model on how bank management team would like To build and train a simple, deep neural network model to predict the likelihood off customers buying personal loans based on their features, such as their age, experience, income, family education and credit card information as well. And you can simply apply this project to predict customer's credit worthiness and also increase the effectiveness off the bank Marketing strategy. In the second module We have built Credit Card Fraud Detection using Artificial neural network AlgorithmThis project requires basic python programming and basic knowledge of machine learning as well. we divided the project into a series off manageable cells. The bank management team would like to build, train and deploy a simple, deep neuron network model that will be able to predict the likelihood off liability customers. And when we say liability customers, these are depositor customers. These are people or customers who deposit money in the bank. And simply the bank would like to identify those customers and kind of, like make them by personal loans. So the idea here is to try to essentially make money. We want them to issue them loans so the bank would be able to charge them interest and The point is, we wanted to target those customers. So to do that, we want to know their age, their experience, their income level, their location, family education level, existing mortgage if they have an existing mortgage with the bank or not. And we also want to know if they have a credit card with our bank account or not, because all these factors play a big role in the acceptance off customers. To these marketing strategies, which is again asking them to buy our personal loans. So ,there is a company or a startup named Lindo included a link here the website and it's actually leading startup that uses advanced machine learning strategies to analyze over 12,000 features from various customers. And the idea here is that we wanted to predict the customer's credit worthiness so it actually go beyond the banking information so you can look at social media account use geo location, data, tons of information that can kind of tell you if this customer has a high credit worthiness or not. Credit card transaction fraud costs billions of dollars to card issuers every year. A well developed fraud detection system with a state-of-the-art fraud detection model is regarded as essential to reducing fraud losses. New advances in electronic commerce systems and communication technologies have made the credit card the potentially most popular method of payment for both regular and online purchases thus, there is significantly increased fraud associated with such transactions. The detection of fraudulent transactions has become a significant factor affecting the greater utilization of electronic payment.
"Loan predictive analysis and credit card fraud detection using Artificial neural networks", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.6, Issue 6, page no.91 - 104, June-2021, Available :https://ijsdr.org/papers/IJSDR2106014.pdf
Volume 6
Issue 6,
June-2021
Pages : 91 - 104
Paper Reg. ID: IJSDR_193389
Published Paper Id: IJSDR2106014
Downloads: 000347233
Research Area: Engineering
Country: Nagpur, Maharashtra, India
ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJSDR(IJ Publication) Janvi Wave
