Regular issue | 2021
Anomaly Detection Algorithms in Financial Data
Abstract
The main aim of this project is to understand and apply\nthe separate approach to classify fraudulent transactions in a\ndatabase using the Isolation forest algorithm and LOF algorithm\ninstead of the generic Random Forest approach. The model will be\nable to identify transactions with greater accuracy and we will\nwork towards a more optimal solution by comparing both\napproaches. The problem of detecting credit card fraud involves\nmodelling past credit card purchases with the perception of those\nthat turned out to be fraud. Then, this model is used to determine\nwhether or not a new transaction is fraudulent. The objective of\nthe project here is to identify 100% of the fraudulent transactions\nwhile mitigating the incorrect classifications offraud.