• Introduction • Why this Topic? • Dataset and its Types. • System Architecture. • Challenges in Credit Card Fraud Detection • System Description • Conclusion • BIBLIOGRAPHY Introduction • Credit card generally refers to a card that is assigned to the customer (cardholder), usually allowing them to purchase goods and services within the credit limit or withdraw cash in advance. • Fraud in credit card transactions is the unbidden use of someone’s account without the owner being aware of it. Credit card frauds are easy targets. • Fraudsters always try to make every fraudulent transaction legitimate, which makes fraud detection a very challenging and difficult task to detect. • There are many machine learning techniques to overcome this problem. • Our project aims to prevent such fraudulent practices by analyzing and studying these fraud transactions to avoid similar situations in the upcoming transactions. Why this Topic? • Generate more sales with good customers: The main purpose of fraud detection technology is to detect bad customers. What’s less obvious is how you can use the technology to do more sales with the good customers once you know who they are?You can use the data collected through the fraud detection process to understand your customers better – find out what their average cart value is, how often they shop with you, and the kinds of items they buy. So you can sell more often and with higher-dollar transactions to good customers. • Increase authorization rates: An authorization rate, also known as an approval ratio or rate, is the percent of transactions that are approved through the authorization process. When you submit a transaction for authorization, the cardholder’s issuing bank reviews the transaction and either approves or denies the request. • Reduce reserve account requirements: A merchant account reserve is money your acquiring bank or processor sets aside in case of emergencies. It’s similar to a security deposit for an apartment rental or collateral for a loan.If you have a merchant account reserve, it’s probably because your payment processor thinks you’re risky.But if you keep fraud risks down and reduce chargebacks, you can prove to the payment processor that you aren’t as risky as they assumed. And they might ease up on reserve requirements — thus, more revenue in your pocket. What is Dataset and Types of Data present in Dataset? • A Dataset is a set or collection of data. This set is normally presented in a tabular pattern. Every column describes a particular variable. And each row corresponds to a given member of the data set, as per the given question. This is a part of data management. Data sets describe values for each variable for unknown quantities such as height, weight, temperature, volume, etc., of an object or values of random numbers. Types of Data • Structured Data: The data which is to the point, factual, and highly organized is referred to as structured data. It is quantitative in nature, i.e., it is related to quantities that means it contains measurable numerical values like numbers, dates, and times. • Unstructured Data: All the unstructured files, log files, audio files, and image files are included in the unstructured data. Some organizations have much data available, but they did not know how to derive data value since the data is raw. SYSTEM ARCHITECTURE
• This is a block diagram for our system. It is
the actual representation of the algorithm which we implemented. The first step is to read the data set and then it is sent for sampling. Training and testing of the data set is done. Cont…… • After the feature selection, the data will be sent to the algorithm which is the combination of the logistic regression, decision tree, random forest & MCC. The resultant data is stored in test sample data. The prediction of outcome is done Based on test sample data & the result of the combined algorithm. Later the performance & accuracy results are plotted. It has a feature which validates the results if the transaction is legitimate then the transaction is said to be true or else it is false. In case of false transactions the bank is made aware of it. Challenges in Credit Card Fraud Detection
• The challenges involved in credit card fraud detection project is primarily
the data itself. The data is heavily imbalanced, i.e., the count of data labeled as fraudulent is way less than the data labeled as non-fraudulent data. This makes it extremely tricky to train the model as it tends to overfit for the majority class and underfit for the minority class. Techniques like oversampling, undersampling, cost-sensitive learning, etc. can be used to deal with this. The metrics used for the final model are different from standard evaluation metrics of accuracy, AUC-ROC, etc. • Another prevalent faced challenge is the quality and quantity of the data. The startups in the early stage do not have much user history data to train extensive models, which makes it difficult to train a robust fraud detection model. A temporary solution to this problem can be sourcing data from an external third party, like scores from credit bureaus. SYSTEM DISCRIPTION:
HARDWARE AND SOFTWARE REQUIREMENTS: -
• The implementation requirements are given in this section. Software : 1. Operating system : Windows 8/10. 2. IDE Tool : Visual Studios and Python Colaboratry notebook 3. Coding Language : Python 3.6 & up 4. APIs : Numpy, pandas, Matplotlib,imblearn Hardware : 1. Processor : Pentium i3 or higher. 2. RAM : 4 GB or higher. Conclusion • Credit card fraud is an act of criminal dishonesty. This paper has various machine learning algorithms. All these techniques are tested based on accuracy and precision. We have selected supervised learning technique Random Forest to classify the alert as fraudulent or authorized. This classifier will be trained using feedback and delayed supervised samples. Next it will aggregate each probability to detect alerts. Further we proposed a learning to rank approach where alerts will be ranked based on priority. BIBLIOGRAPHY
[1] Vaishnavi Nath Dornadulaa, Geetha S. Credit Card
Fraud Detection using Machine Learning Algorithms. IJCSMC, 2019, https://www.sciencedirect.com/science/article/pii/S1877 050 92030065X. [2] Lakshmi S V S S, Selvani Deepthi Kavila, (2018), Machine Learning For Credit Card Fraud Detection System, Research India Publications [3] https://www.kaggle.com/ntnu-testimon/paysim1/home Thank You