Predicting Fraud Victimization Using Classical Machine Learning

Abstract

Protecting financial consumers from investment fraud has been a recurring problem in Canada. The purpose of this paper is to predict the demographic characteristics of investors who are likely to be victims of investment fraud. Data for this paper came from the Investment Industry Regulatory Organization of Canada’s (IIROC) database between January of 2009 and December of 2019. In total, 4575 investors were coded as victims of investment fraud. The study employed a machine-learning algorithm to predict the probability of fraud victimization. The machine learning model deployed in this paper predicted the typical demographic profile of fraud victims as investors who classify as female, have poor financial knowledge, know the advisor from the past, and are retired. Investors who are characterized as having limited financial literacy but a long-time relationship with their advisor have reduced probabilities of being victimized. However, male investors with low or moderate-level investment knowledge were more likely to be preyed upon by their investment advisors. While not statistically significant, older adults, in general, are at greater risk of being victimized. The findings from this paper can be used by Canadian self-regulatory organizations and securities commissions to inform their investors’ protection mandates.

The determinants of investment fraud: A machine learning and artificial intelligence approach

“…There is an association between male investment advisors and female investors. These findings suggest that male advisors are more likely to gain the trust of female advisors and swindle them in return (see Kadoya et al, 2021;Knüpfer et al, 2021;Lokanan and Liu, 2021).…”

“…Women are increasingly taking control of their finances and responsible for household financial management (Rutterford and Maltby, 2007 ; Lusardi, 2012 ). Therefore, it is not surprising that as more women take control of their household finance, their increased participation in the financial markets will also lead to them being more likely victims of investment fraud (see Lusardi, 2012 ; Deliema et al, 2020 ; Lokanan and Liu, 2021 ).…”

“…and not proportionate to the harm caused by the offense (Gray and McFarland, 2013;Fair Canada, 2014;Canadian Securities Administrators, 2020;Lokanan and Liu, 2021).…”

“…Research confirmed that fraud detection is an ongoing problem for regulators and encouraged them to raise their profile and find ways to ensure earlier detection and intervention of investment fraud (Fair Canada, 2014 ; Canadian Securities Administrators, 2020 ). When fraud is detected, investment advocates argue that enforcement is weak and that the imposition of penalties by SROs have been inconsistent and not proportionate to the harm caused by the offense (Gray and McFarland, 2013 ; Fair Canada, 2014 ; Canadian Securities Administrators, 2020 ; Lokanan and Liu, 2021 ).…”

Supply Chain Fraud Prediction with Machine Learning and Artificial intelligence

“…S(t) is a logistic sigmoid function that modi es and categorizes the linear function b + b'X into two or more discrete categories [4]. Logistic regression is very bene cial for detecting fraud since it may offer a ranking order of the classi ed data set based on the likelihood of fraud versus no-fraud observations [27]. Logistic regression examines each transaction and assigns a probability to it, which is then used to determine whether the transaction is fraudulent.…”