Does cognitive biased knowledge influence investor decisions? An empirical investigation using machine learning and artificial neural network

Abstract

Purpose

Current research in the field of behavioural finance has attempted to discover behavioural biases and their characteristics in individual investors’ irrational decision-making. This study aims to find out how biases in information based on knowledge affect decisions about investments.

Design/methodology/approach

In step one, through existing research and consultation with specialists, 13 relevant items covering major aspects of bias were determined. In the second step, multiple linear regression and artificial neural network were used to analyse the data of 337 retail investors.

Findings

The investment choice was heavily impacted by regret aversion, followed by loss aversion, overconfidence and the Barnum effect. It was observed that the Barnum effect has a statistically significant negative link with investing choices. The research also found that investors’ fear of making mistakes and their tendency to be too sure of themselves were the most significant factors in their decisions about where to put their money.

Practical implications

This research contributes to the expansion of the knowledge base in behavioural finance theory by highlighting the significance of cognitive psychological traits in how leading investors end up making irrational decisions. Portfolio managers, financial institutions and investors in developing markets may all significantly benefit from the information offered.

Originality/value

This research is a one-of-a-kind study, as it analyses the emotional biases along with the cognitive biases of investor decision-making. Investor decisions generally consider the shadowy side of knowledge management.

Citation

Bihari, A., Dash, M., Muduli, K., Kumar, A., Mulat-Weldemeskel, E. and Luthra, S. (2025), "Does cognitive biased knowledge influence investor decisions? An empirical investigation using machine learning and artificial neural network", VINE Journal of Information and Knowledge Management Systems, Vol. 55 No. 2, pp. 445-469. https://doi.org/10.1108/VJIKMS-08-2022-0253