Classification of e-commerce financial transaction logs using machine learning approach

Abstract

E-Commerce becomes inevitable in the current world. Especially in this pandemic period, almost activities have been carried out through digital mode to serve the customers with more safety. The financial transactions are much secured in the e-commerce payment. Still, many intruders are making these transactions into fail and hacking the customers’ information when the financial transactions are carried out. Along with, sometimes the transactions may get failed due to the network issues. Hence, the E-Commerce organizations are maintaining the transaction logs to check and take necessary action over the failed transactions. Out of huge transaction logs, identifying the suspicious failed transactions in manual method is not encouraged. Lot of technologies have come to support the detection of suspicious failed transactions such as Artificial Neural Network, Machine Learning, Deep Learning and other statistical methods. As the above methods are proved as more suitable for detecting and classifying the failed transaction logs, still the accuracy of classification has not been achieved much, which motivated to propose the machine learning based classification of E-Commerce Financial Transaction Logs.