Predicting savings adequacy using machine learning: A behavioural economics approach
Document Type
Article
Publication Date
10-1-2022
Abstract
This paper proposes a machine-learning-based method that can predict individuals' savings adequacy in the presence of mental accounting. The proposed predictive model perceives wealth and consumption, each of which is being divided into three non-fungible distinct classes. The predictive model has found that the mental accounting categories have predictive power on savings adequacy, whereby the emphasis is that the expenditure on luxury items is followed by the total current asset. Savings adequacy is best predicted by the decision tree model based on the Malaysian Ageing and Retirement (MARS) survey data. Surprisingly, it was found that future income and necessities had a lower predictive power on savings adequacy. The findings suggests that individuals, financial professionals, and policymakers should be cognizant that higher likelihood of achieving savings adequacy can be achieved by focusing on accumulation of current asset while lowering expenditure on luxury items.
Keywords
Behavioural finance, Economics, Human decision-making, Psychology
Divisions
Faculty_of_Business_and_Accountancy
Funders
None
Publication Title
Expert Systems with Applications
Volume
203
Publisher
Elsevier
Publisher Location
THE BOULEVARD, LANGFORD LANE, KIDLINGTON, OXFORD OX5 1GB, ENGLAND