Download PDFOpen PDF in browser

Credit Card Fraud Detection Using Machine Learning

EasyChair Preprint no. 5616

7 pagesDate: May 26, 2021


Whenever we hear the word Credit Card the first thing that pops in our mind is the frauds that are associated with these cards. Credit card has become an indispensable part of our lives. Although a credit card has many advantages when used in a proper manner but damages can be caused to it by many fraudulent activities as well. But in today’s advanced world these frauds can be detected with a vast knowledge of machine learning algorithms. The Credit Card Anomaly Detection Problem includes modeling past credit card transactions with the ones thatturned out to be fraud. After the implementation of this model we can use it further to identify, a new transaction that is occurring as fraudulent or not. Basically our focus here is to detect 100% fraud transactions that is being occur by minimizing the incorrect fraud classification. This detection process is a typical example of classifications. This process involve the analysis and the pre-processing of data sets as well as the utilization of multiple Anomaly detection algorithms such as Local Outlier Factor, Super Vector Machine and many such relevant algorithms. In today's world this is the major concern, which demands the attention of the fields such as Machine Learning, Artificial Intelligence, Deep Learning etc. where the solution of this issue can be automated. Our aim is to predict the accuracy/precision of the fraud detection through different algorithms. Further this analysis can be used to implement the fraud detection model.

Keyphrases: Artificial Intelligence, comparative analysis, Credit Card Fraud Classification, Data Science, dataset, fraud detection, Machine Learning Algorithm, Python, Techniques

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
  author = {Harshita Anand and Richa Gautam and Raman Chaudhry},
  title = {Credit Card Fraud Detection Using Machine Learning},
  howpublished = {EasyChair Preprint no. 5616},

  year = {EasyChair, 2021}}
Download PDFOpen PDF in browser