DeepAI AI Chat
Log In Sign Up

Adaptive Fraud Detection System Using Dynamic Risk Features

10/10/2018
by   Huiying Mao, et al.
Microsoft
Virginia Polytechnic Institute and State University
0

eCommerce transaction frauds keep changing rapidly. This is the major issue that prevents eCommerce merchants having a robust machine learning model for fraudulent transactions detection. The root cause of this problem is that rapid changing fraud patterns alters underlying data generating system and causes the performance deterioration for machine learning models. This phenomenon in statistical modeling is called "Concept Drift". To overcome this issue, we propose an approach which adds dynamic risk features as model inputs. Dynamic risk features are a set of features built on entity profile with fraud feedback. They are introduced to quantify the fluctuation of probability distribution of risk features from certain entity profile caused by concept drift. In this paper, we also illustrate why this strategy can successfully handle the effect of concept drift under statistical learning framework. We also validate our approach on multiple businesses in production and have verified that the proposed dynamic model has a superior ROC curve than a static model built on the same data and training parameters.

READ FULL TEXT

page 1

page 2

page 3

page 4

05/12/2020

Handling Concept Drift for Predictions in Business Process Mining

Predictive services nowadays play an important role across all business ...
11/05/2020

Switching Scheme: A Novel Approach for Handling Incremental Concept Drift in Real-World Data Sets

Machine learning models nowadays play a crucial role for many applicatio...
06/16/2020

Consistent Recalibration Models and Deep Calibration

Consistent Recalibration models (CRC) have been introduced to capture in...
04/01/2020

Handling Concept Drifts in Regression Problems – the Error Intersection Approach

Machine learning models are omnipresent for predictions on big data. One...
11/12/2015

Characterizing Concept Drift

Most machine learning models are static, but the world is dynamic, and i...
09/07/2018

Revisiting Inaccuracies of Time Series Averaging under Dynamic Time Warping

This article revisits an analysis on inaccuracies of time series averagi...