Cookies

We use cookies to ensure that we give you the best experience on our website. You can change your cookie settings at any time. Otherwise, we'll assume you're OK to continue.

Durham University

Research & business

View Profile

Publication details for Professor Nigar Hashimzade

Hashimzade, N. & Myles, G. (2017). Risk-Based Audits in a Behavioural Model. Public Finance Review 45(1): 140-165.

Author(s) from Durham

Abstract

The tools of predictive analytics are widely used in the analysis of large data sets to predict future patterns in the system. In particular, predictive analytics is used to estimate risk of engaging in certain behavior. Risk-based audits are used by revenue services to target potentially noncompliant taxpayers, but the results of predictive analytics serve predominantly only as a guide rather than a rule. “Auditor judgment” retains an important role in selecting audit targets. This article assesses the effectiveness of using predictive analytics in a model of the compliance decision that incorporates several components from behavioral economics: subjective beliefs about audit probabilities, a social custom reward from honest tax payment, and a degree of risk aversion that increases with age. Simulation analysis shows that predictive analytics are successful in raising compliance and that the resulting pattern of audits is very close to being a cutoff rule.