Stock Market Bubble Warning: A Restricted Boltzmann Machine Approach Using Volatility–Return Sequences

Combining unsupervised learning with Restricted Boltzmann Machines and supervised learning with Balanced Random Forest and Feedforward Neural Networks, we propose a warning system for the early detection of stock bubbles by analyzing daily returns and the volatility of a market index. We complement our method by detecting states of high volatility and very low returns, which are market states that immediately follow a stock market’s bubble-bursting point. We trained our detection model using the S&P500 as an empirical case study, using successive samples of well-known crises from 1987 to 2022. Our results achieve area-under-the-curve (AUC) rates of over 70% and false-positive rates of less than 20%. Our model’s generative nature enables the creation of synthetic samples to analyze market periods prone to forming a bubble. The model successfully alerts periods of bubbles and instability in the stock market. Capital markets’ interconnectedness enables the model to be trained with various shocks from other stock markets, providing further detection learning possibilities and improved detection rates. Our work helps investors, regulators, and practitioners in their stock market investment, supervision, and monitoring tasks.