Can Alert Models for Fraud Protect the Elderly Clients of a Financial Institution?

27 Pages Posted: 23 Aug 2018 Last revised: 28 Nov 2018

See all articles by Gaurav Kumar

Gaurav Kumar

University College Dublin (UCD)

Cal B. Muckley

University College Dublin

Linh Pham

Michael Smurfit Graduate School of Business

Darragh Ryan

University College Dublin (UCD)

Date Written: November 8, 2018

Abstract

Using account-level transaction data at a major financial institution, we predict the incidence of suspicious activity that can be related to the external financial fraud of its elderly clients. The data consists of over 5 million accounts of clients aged 70 years and older, and over 250 million transactions extending from January 2015 to August 2016. Our main focus is to improve the detection of alerts within a proprietorial transaction monitoring system. Using logistic regression, random forest and support vector machine learning techniques, together with corrections for imbalanced alert samples, we provide a new alert model for the protection of elderly clients at a financial institution, with out-of-sample predictive accuracy. Our findings show the relative influence of client traits and account activity in our select external fraud alert models.

Keywords: alert models, fraud, elderly clients, financial institutions, machine learning

JEL Classification: G21, G17, D12, C55

Suggested Citation

Kumar, Gaurav and Muckley, Cal B. and Pham, Linh and Ryan, Darragh, Can Alert Models for Fraud Protect the Elderly Clients of a Financial Institution? (November 8, 2018). Michael J. Brennan Irish Finance Working Paper Series Research Paper No. 18-16, Available at SSRN: https://ssrn.com/abstract=3230188 or http://dx.doi.org/10.2139/ssrn.3230188

Gaurav Kumar

University College Dublin (UCD) ( email )

Belfield
Belfield, Dublin 4 4
Ireland

Cal B. Muckley (Contact Author)

University College Dublin ( email )

Blackrock, Co. Dublin
Ireland
+353-1-716-8091 (Phone)

Linh Pham

Michael Smurfit Graduate School of Business ( email )

Blackrock
Ireland

Darragh Ryan

University College Dublin (UCD) ( email )

Belfield
Belfield, Dublin 4 4
Ireland

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
202
Abstract Views
1,364
Rank
272,294
PlumX Metrics