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...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/10/5613 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849327770044203008 |
|---|---|
| author | Mauricio A. Valle Jaime Lavín Felipe Urbina |
| author_facet | Mauricio A. Valle Jaime Lavín Felipe Urbina |
| author_sort | Mauricio A. Valle |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-07b92ef20bb44b0bbee6d95236ee105b |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-07b92ef20bb44b0bbee6d95236ee105b2025-08-20T03:47:48ZengMDPI AGApplied Sciences2076-34172025-05-011510561310.3390/app15105613Stock Market Bubble Warning: A Restricted Boltzmann Machine Approach Using Volatility–Return SequencesMauricio A. Valle0Jaime Lavín1Felipe Urbina2Facultad de Ingeniería y Ciencias, Universidad Adolfo Ibáñez, Av. Diag. Las Torres 2640, Santiago 7941169, ChileEscuela de Negocios, Universidad Adolfo Ibáñez, Av. Diag. Las Torres 2640, Santiago 7941169, ChileCentro Multidisciplinario de Física, Universidad Mayor, Santiago 8580745, ChileCombining 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.https://www.mdpi.com/2076-3417/15/10/5613stockbubblesrestricted Boltzmann machineartificial neural networksbalanced random forestregime changes |
| spellingShingle | Mauricio A. Valle Jaime Lavín Felipe Urbina Stock Market Bubble Warning: A Restricted Boltzmann Machine Approach Using Volatility–Return Sequences Applied Sciences stockbubbles restricted Boltzmann machine artificial neural networks balanced random forest regime changes |
| title | Stock Market Bubble Warning: A Restricted Boltzmann Machine Approach Using Volatility–Return Sequences |
| title_full | Stock Market Bubble Warning: A Restricted Boltzmann Machine Approach Using Volatility–Return Sequences |
| title_fullStr | Stock Market Bubble Warning: A Restricted Boltzmann Machine Approach Using Volatility–Return Sequences |
| title_full_unstemmed | Stock Market Bubble Warning: A Restricted Boltzmann Machine Approach Using Volatility–Return Sequences |
| title_short | Stock Market Bubble Warning: A Restricted Boltzmann Machine Approach Using Volatility–Return Sequences |
| title_sort | stock market bubble warning a restricted boltzmann machine approach using volatility return sequences |
| topic | stockbubbles restricted Boltzmann machine artificial neural networks balanced random forest regime changes |
| url | https://www.mdpi.com/2076-3417/15/10/5613 |
| work_keys_str_mv | AT mauricioavalle stockmarketbubblewarningarestrictedboltzmannmachineapproachusingvolatilityreturnsequences AT jaimelavin stockmarketbubblewarningarestrictedboltzmannmachineapproachusingvolatilityreturnsequences AT felipeurbina stockmarketbubblewarningarestrictedboltzmannmachineapproachusingvolatilityreturnsequences |