Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 67 - Section on Statistical Computing: Data Science
Type: Contributed
Date/Time: Monday, August 3, 2020 : 10:00 AM to 2:00 PM
Sponsor: Section on Statistical Computing
Abstract #313811
Title: A Simple and Scalable Algorithm for Anomaly Identification with an Application in Credit Card Fraud Detection
Author(s): Cheng Peng*
Companies: West Chester University of Pennsylvania
Keywords: Anomaly Identification; Machine Learning Algorithm; Bootstrap; Process Capability Index; Control Charting; Fraud Detection
Abstract:

We present a simple and scalable algorithm for anomaly identification using the control chart based on the process capability indices of any processes that generate numeric characteristics in a sequential manner. The algorithm can be considered as a machine learning algorithm and used standalone for anomaly identification or classification. It can also be used as a method of feature extraction that aggregates information from sequence data. A simple version of the algorithm has been successfully implemented in a real-time production environment for credit card fraud detection. As an example, I will present an application of the algorithm as a fraud detection tool on a static credit card transaction data.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2020 program