Advanced Time Series Modeling for High-Risk Financial Instruments Using VRA-Enhanced Machine Learning
Received: 25 November 2025 | Revised: 3 February 2026, 6 March 2026, 30 March 2026, 11 April 2026, and 21 April 2026 | Accepted: 23 April 2026 | Online: 6 June 2026
Corresponding author: Ritu Chauhan
Abstract
Financial markets face frequent volatility and rapid regime shifts, which lead to uncertainty and risk for investors and financial institutions. This can be addressed by building a model that remains reliable under changing conditions and detects rare but impactful high-risk events. However, building such a model constitutes a great challenge. Individual Machine Learning (ML) models can capture complex nonlinear patterns. However, they often face a trade-off between recall and precision as models optimized for recall tend to produce many false alarms, whereas models with higher accuracy may miss significant risk episodes. The current study addresses this issue by proposing the Volatility Risk Analyzer (VRA), a hybrid prediction framework combining both supervised and unsupervised learning techniques. Unsupervised regime detection is performed using K-means clustering, and Long Short-Term Memory (LSTM) networks are utilized to model temporal dynamics in financial time-series data. The clustering outputs are integrated employing a hybrid training technique to exploit their complementary strengths. The proposed framework is evaluated using an external dataset of five years of ICICI Bank OHLCV stock data, supplemented with widely deployed technical indicators such as Moving Averages, Moving Average Convergence Divergence (MACD), Rate of Change (ROC), and Williams %R. The results indicate that combining supervised and unsupervised learning enhances volatility risk prediction, offering a novel contribution for both academic research and real-world risk management applications.
Keywords:
volatility risk prediction, LSTM, K-means, financial time series, volatility riskReferences
H. T. Araya, J. Aduda, and T. Berhane, "A Hybrid GARCH and Deep Learning Method for Volatility Prediction," Journal of Applied Mathematics, vol. 2024, no. 1, Jan. 2024, Art. no. 6305525.
E. Koo and G. Kim, "A Hybrid Prediction Model Integrating GARCH Models with a Distribution Manipulation Strategy Based on LSTM Networks for Stock Market Volatility," IEEE Access, vol. 10, pp. 34743–34754, 2022.
L. Zhang, L. Dai, F. Wang, Y. Zhao, J. Wu, and Q. Yu, "Research on Financial Prediction Based on LSTM-GARCH Hybrid Model," in IEEE 2nd International Conference on Electrical, Automation and Computer Engineering, Changchun, China, Dec. 2024, pp. 513–518.
N. Siddiraju and R. Hasan, "A Hybrid LSTM-GARCH Network for Stock Market Volatility Prediction," in IEEE 15th Annual Computing and Communication Workshop and Conference, Las Vegas, NV, USA, Jan. 2025, pp. 427–433.
L. Yang, Q. Wu, S. Liang, S. Mu, Z. Xue, and Y. Yang, "A Study on Financial Time Series Forecasting Based on LSTM-GARCH Modeling," in IEEE 2nd International Conference on Electrical, Automation and Computer Engineering, Changchun, China, Dec. 2024, pp. 742–746.
W. Feng, Y. Li, and X. Zhang, "A Mixture Deep Neural Network GARCH Model for Volatility Forecasting," Electronic Research Archive, vol. 31, no. 7, pp. 3814–3831, 2023.
J. Zhou, "Predicting Stock Price by Using Attention-Based Hybrid LSTM Model," Asian Journal of Basic Science & Research, vol. 6, no. 2, pp. 145–158, 2024.
B. Dong, "Prediction of Stock Market Volatility and Bond Risk Based on Deep Learning," Applied and Computational Engineering, vol. 114, no. 1, pp. 203–209, Dec. 2024.
R. Zhu, Y. Yang, and J. Chen, "XGBoost and CNN-LSTM Hybrid Model with Attention-Based Stock Prediction," in IEEE 3rd International Conference on Electronic Technology, Communication and Information, Changchun, China, May 2023, pp. 359–365.
L. Liang, "ARIMA with Attention-Based CNN-LSTM and XGBoost Hybrid Model for Stock Prediction in the US Stock Market," SHS Web of Conferences, vol. 196, 2024, Art. no. 02001.
M. El Mahjouby, K. El Fahssi, M. Taj Bennani, M. Lamrini, and M. El Far, "Machine Learning Techniques for Predicting and Classifying Exchange Rates between US Dollars and Japanese Yen," Engineering, Technology & Applied Science Research, vol. 14, no. 5, pp. 16266–16271, Oct. 2024.
M. B. Shiraj, M. Rahman, M. Al-Imran, M. Z. A. Liza, M. Murshed, and N. Akhter, "Anomaly Detection in Financial Time Series Data via Mapper Algorithm and DBSCAN Clustering," World Journal of Advanced Engineering Technology and Sciences, vol. 13, no. 1, pp. 070–084, Sep. 2024.
S. Kumar, A. Rao, and M. Dhochak, "Hybrid ML Models for Volatility Prediction in Financial Risk Management," International Review of Economics & Finance, vol. 98, Mar. 2025, Art. no. 103915.
K. Mohan, "ICICI-NSE OHLCV Market Data." Kaggle, Mar. 2026, [Online]. Available: https://www.kaggle.com/datasets/kapilmohan13/icici-nse-ohlcv-market-data.
H. Gupta, R. Aafrein, R. Kumari, S. Rajput, and N. Puri, "Forecasting Commodity Prices Using Machine Learning," International Journal of Scientific Research in Science and Technology, pp. 81–89, Jan. 2024.
K. Saetia and J. Yokrattanasak, "Stock Movement Prediction Using Machine Learning Based on Technical Indicators and Google Trend Searches in Thailand," International Journal of Financial Studies, vol. 11, no. 1, Dec. 2022, Art. no. 5.
P. Tang, C. Tang, and K. Wang, "Stock Movement Prediction: A Multi‐Input LSTM Approach," Journal of Forecasting, vol. 43, no. 5, pp. 1199–1211, Aug. 2024.
Y. Zhai, "Comparison of the Performance of Different Machine Learning Methods in Predicting VIX Volatility," Advances in Economics, Management and Political Sciences, vol. 85, no. 1, pp. 69–75, May 2024.
Downloads
How to Cite
License
Copyright (c) 2026 Kapil Mohan, Ritu Chauhan, Harleen Kaur
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
