Hybrid ML models for volatility prediction in financial risk management

Zahrani Aulia; Annisa Qurrota A’yun

doi:10.69725/ami.v1i1.236

Authors

Zahrani Aulia Management Department at the Vocational School of Universitas Diponegoro, Indonesia
Annisa Qurrota A’yun Management Department at the Vocational School, Universitas Diponegoro, Indonesia.

DOI:

https://doi.org/10.69725/ami.v1i1.236

Keywords:

Volatility Prediction, Market Sentiment, Noise Decomposition, Reinforcement Learning, Financial Risk

Abstract

Purpose: We examine the impacts of financial news sentiment, investor attention, market microstructure and macroeconomic timing in influencing realised volatilities of financial assets.
Method: Building a hybrid framework with the Q-learning adaptableness and the Variational Mode Decomposition, moderated mediation analysis are conducted based on the cross sectional behaviour and high-frequency structure data.
Findings: All four of sentiment, attention, microstructure and announcement timing exert a significant impact on realized volatility. Market noise decomposition partially mediates these links, and model adaptiveness attenuates their effects. The interplay between behavioural signals and structural flows is also heavily influenced by adaptive AI dynamics, showing volatility to be multi causal, feedback driven.
Novelty: We develop a two layer AI behavioural econometric framework in which dissected market noise and Q-learning adaptiveness simultaneously account for volatility, providing a novel combination of signal processing and reinforcement learning in the finance field.
Implications: Results offer tangible implications for adaptive risk model applications, behaviour aware stress testing, and risk measurement in markets with nonlinear dynamics consulting academic and industry expansions in finance risk practices

Downloads

Download data is not yet available.

Author Biographies

Zahrani Aulia, Management Department at the Vocational School of Universitas Diponegoro, Indonesia

Zahrani Aulia is an academic and researcher affiliated with the Management Department at the Vocational School of Universitas Diponegoro, Indonesia. Her academic interest focuses on business management, digital transformation in vocational education, and the development of entrepreneurial competencies among students. She actively participates in applied research and community engagement projects that promote innovation and sustainability in micro and small enterprises (MSMEs). Zahrani has contributed to institutional initiatives that bridge academic theory with practical business solutions, particularly within the context of Indonesia’s vocational higher education landscape.
Annisa Qurrota A’yun, Management Department at the Vocational School, Universitas Diponegoro, Indonesia.

Annisa Qurrota A’yun, S.E., M.M. is a senior lecturer and researcher in the Management Department at the Vocational School, Universitas Diponegoro, Indonesia. Her research areas include strategic management, human capital development, and innovation in vocational business education. As an active contributor to scholarly work, she has published in several indexed journals and is listed as a Scopus-author (ID: 57245851300). Annisa also serves as a reviewer and research supervisor, supporting initiatives that integrate academic research with industry needs. Her work often emphasizes collaboration between academic institutions and local enterprises to enhance entrepreneurial ecosystems and policy relevance.

References

Abdoos, Ali Akbar. 2016. “A New Intelligent Method Based on Combination of VMD and ELM for Short Term Wind Power Forecasting.” Neurocomputing 203:111–20. doi: https://doi.org/10.1016/j.neucom.2016.03.054.

Bandauko, Elmond, and Godwin Arku. 2025. “Navigating Political Opportunity Structures: Street Traders’ Associations and Collective Action in Politically Volatile Urban Environments.” Political Geography 118:103292. doi: https://doi.org/10.1016/j.polgeo.2025.103292.

Easley, David, and Maureen O’Hara. 1987. “Price, Trade Size, and Information in Securities Markets.” Journal of Financial Economics 19(1):69–90. doi: https://doi.org/10.1016/0304-405X(87)90029-8.

Gao, Jie, Chunguo Fan, Liang Xu, Hongni Chen, Hangyu Chen, and Zhilei Liang. 2025. “Intelligent Decision Making and Risk Management in Stock Index Futures Markets under the Influence of Global Geopolitical Volatility.” Omega 133:103272. doi: https://doi.org/10.1016/j.omega.2024.103272.

Goyal, Kirti, Sudipta Kumar Nanda, and Monika Agrawal. 2025. “Psychological Echoes: Exploring Investor Sentiments Across Market Events.” Journal of Economic Surveys n/a(n/a). doi: https://doi.org/10.1111/joes.12701.

Hautsch, Nikolaus, Dieter Hess, and David Veredas. 2011. “The Impact of Macroeconomic News on Quote Adjustments, Noise, and Informational Volatility.” Journal of Banking & Finance 35(10):2733–46. doi: https://doi.org/10.1016/j.jbankfin.2011.03.004.

Ibrahim, Mahat Maalim, Asad Ul Islam Khan, and Muhittin Kaplan. 2025. “From Headlines to Stock Trends: Natural Language Processing and Explainable Artificial Intelligence Approach to Predicting Turkey’s Financial Pulse.” Borsa Istanbul Review. doi: https://doi.org/10.1016/j.bir.2025.06.013.

Jeremy Chiu, Ching-wai, Richard D. F. Harris, Evarist Stoja, and Michael Chin. 2018. “Financial Market Volatility, Macroeconomic Fundamentals and Investor Sentiment.” Journal of Banking & Finance 92:130–45. doi: https://doi.org/10.1016/j.jbankfin.2018.05.003.

Lan, Tian, and Michael Frömmel. 2025. “Risk Factors in Cryptocurrency Pricing.” International Review of Financial Analysis 105:104389. doi: https://doi.org/10.1016/j.irfa.2025.104389.

Li, Yuze, Shangrong Jiang, Xuerong Li, and Shouyang Wang. 2021. “The Role of News Sentiment in Oil Futures Returns and Volatility Forecasting: Data-Decomposition Based Deep Learning Approach.” Energy Economics 95:105140. doi: https://doi.org/10.1016/j.eneco.2021.105140.

Liu, Wei, Jiashen Teh, and Bader Alharbi. 2025. “An Asynchronous Electro-Thermal Coupling Modeling Method of Lithium-Ion Batteries under Dynamic Operating Conditions.” Energy 324:135890. doi: https://doi.org/10.1016/j.energy.2025.135890.

Liu, Xuefeng, Zhixin Wu, and Jiayue Xin. 2025. “Forecasting Stock Market Time Series through the Integration of Bee Colony Optimizer and Multivariate Empirical Mode Decomposition with Extreme Gradient Boosting Regression.” Engineering Applications of Artificial Intelligence 148:110353. doi: https://doi.org/10.1016/j.engappai.2025.110353.

Liu, Yanchen, Siyu Yi, Sitong Li, and Gengxuan Chen. 2025. “Asymmetric Impacts of Energy Market-Related Uncertainty on Clean Energy Stock Volatility: The Role of Extreme Shocks.” International Review of Financial Analysis 103:104206. doi: https://doi.org/10.1016/j.irfa.2025.104206.

De Long, J. Bradford, Andrei Shleifer, Lawrence H. Summers, and Robert J. Waldmann. 1990. “Noise Trader Risk in Financial Markets.” Journal of Political Economy 98(4):703–38. doi: 10.1086/261703.

NAKAI, FATHI, and DONIA ROUIHEM. 2025. “FLUCTUATIONS IN MACROECONOMIC NEWS AND THEIR IMPACT ON THE STOCK MARKET: EVIDENCE FROM THE TUNISIAN TURBULENT PERIODS.” Global Economy Journal 2550003. doi: 10.1142/S2194565925500034.

Nimark, Kristoffer. 2008. “Monetary Policy with Signal Extraction from the Bond Market.” Journal of Monetary Economics 55(8):1389–1400. doi: https://doi.org/10.1016/j.jmoneco.2008.09.004.

Rickles, Dean. 2011. “Econophysics and the Complexity of Financial Markets.” Pp. 531–65 in Handbook of the Philosophy of Science. Vol. 10, edited by C. B. T.-P. of C. S. Hooker. Amsterdam: North-Holland.

Scruggs, John T. 2007. “Noise Trader Risk: Evidence from the Siamese Twins.” Journal of Financial Markets 10(1):76–105. doi: https://doi.org/10.1016/j.finmar.2006.04.002.

Sornette, D., and J. V Andersen. 2002. “A NONLINEAR SUPER-EXPONENTIAL RATIONAL MODEL OF SPECULATIVE FINANCIAL BUBBLES.” International Journal of Modern Physics C 13(02):171–87. doi: 10.1142/S0129183102003085.

Sultana, Nargis, and Fahad Zeya. 2025. “Advancing Firm-Specific ESG Sentiment Analysis: A Machine Learning Approach to Clustering, Prediction, and Financial Performance Implications.” Business Strategy & Development 8(3):e70150. doi: https://doi.org/10.1002/bsd2.70150.

Tang, Yuxuan. 2025. “Decision-Making in M&A Under Market Mispricing: The Role of Deep Learning Models.” Managerial and Decision Economics n/a(n/a). doi: https://doi.org/10.1002/mde.4533.

Tripathy, Nrusingha, Sarbeswara Hota, Debabrata Singh, Biswa Mohan Acharya, and Subrat Kumar Nayak. 2025. “A Comprehensive Analysis of Bitcoin Volatility Forecasting Using Time-Series Econometric Models.” Applied Soft Computing 178:113339. doi: https://doi.org/10.1016/j.asoc.2025.113339.

Wang, Zeyu, Yuelan Hong, Luying Huang, Miaocui Zheng, Hongping Yuan, and Ruochen Zeng. 2025. “A Comprehensive Review and Future Research Directions of Ensemble Learning Models for Predicting Building Energy Consumption.” Energy and Buildings 335:115589. doi: https://doi.org/10.1016/j.enbuild.2025.115589.

Xing, Frank Z., Erik Cambria, and Roy E. Welsch. 2018. “Natural Language Based Financial Forecasting: A Survey.” Artificial Intelligence Review 50(1):49–73. doi: 10.1007/s10462-017-9588-9.

Xu, Jing, and Wudi Xu. 2025. “Exploring the Transmission Pathway of ‘Data-Finance’ Synergistic Clustering on Corporate Economic Adaptability: Evidence from Quasi-Experimental Analysis in National Big Data Pilot Zones.” International Review of Economics & Finance 101:104233. doi: https://doi.org/10.1016/j.iref.2025.104233.

Yanping, Song. 2025. “Customer Loyalty Evaluation Model Based on Improved Particle Swarm Algorithm.” International Journal of High Speed Electronics and Systems 2540742. doi: 10.1142/S0129156425407429.

Zhang, Pengcheng, Kunpeng Xu, Jian Huang, and Jiayin Qi. 2024. “Investor Sentiment and the Holiday Effect in the Cryptocurrency Market: Evidence from China.” Financial Innovation 10(1):113. doi: 10.1186/s40854-024-00639-x.

Zhang, Yagang, Bing Chen, Guifang Pan, and Yuan Zhao. 2019. “A Novel Hybrid Model Based on VMD-WT and PCA-BP-RBF Neural Network for Short-Term Wind Speed Forecasting.” Energy Conversion and Management 195:180–97. doi: https://doi.org/10.1016/j.enconman.2019.05.005.