Cognitive Biases on the Iran Stock Exchange: Unsupervised Learning Approach to Examining Feature Bundles in Investors’ Portfolios

This paper innovatively analyses the joint occurrence of cognitive biases in groups of stock exchange investors. It considers jointly a number of common fallacies: confirmation bias, loss aversion, gambler’s fallacy, availability cascade, hot-hand fallacy, bandwagon effect, and Dunning–Kruger effect, which have hitherto been studied separately. The paper aims to highlight the diverse range of investor’s profiles which are characterised by such fallacies, and the considerable differences observed based on their age, stock market experience and perception of market trends. The analysis is based on k-means and hierarchical clustering, feature importance and Principal Component Analysis, which were applied to data from the Tehran Stock Exchange. There are a few essential findings which contribute to the existing literature. Firstly, the results show that gender does not have a role to play in diversifying the investors’ profiles. Secondly, cognitive biases are bundled, and we distinguish four investors’ profiles; thus, they should be analysed jointly, not separately. Thirdly, the exposure to cognitive biases differs significantly due to the individual features of investors. The group most vulnerable to almost all analysed biases are inexperienced investors, who are pessimistic about market developments and have invested a large amount. Fourthly, the ages of investors are essential only in connection with other factors such as experience, market perception and investment exposure. Young (20–40 years), experienced investors with huge investments (+1000 mln rials/+24,000 USD) are mostly less exposed to all biases and much less risk-averse. Additionally, older (50+) and experienced investors (5–10 years) who are more optimistic about trends (hot hand bias) were affected much less by cognitive biases, only showing vulnerability to the Dunning–Kruger effect. Fifthly, more than 40% of investors apply consultation and technical analysis approaches to succeed in trading. Finally, from a methodological perspective, this study shows that unsupervised learning methods are effective in profiling investors and bundling similar behaviours.