A predictor based method for signal detection in time series case study: financial markets of Iran in COVID-19 outbreak

Document Type : Research Article

Authors

1 Department of Statistics, Amirkabir University of Technology, Tehran, Iran

2 Department of Statistics, Shahid Beheshti University, Tehran, Iran.

3 Department of Mathematics and Statistics, University of Calgary, Calgary, Canada.

Abstract

In this paper, we propose a signal detection method in time series data within the context of the financial markets. By analyzing historical data from the related markets, such as foreign exchange rates and cryptocurrency prices, we aim to identify significant signals affecting the cash price of refined Gold in the Iranian market. Our approach leverages various time series models, including autoregressive integrated moving average, seasonal autoregressive integrated moving average, and neural networks, and also regression-based time series methods to predict fluctuations in Gold prices. We focus on a working days period before and after the onset of the COVID-19 outbreak in Iran on February 23, 2020. To achieve this, we propose a predictor-based algorithm for signal detection that utilizes both traditional time series and regression models. This algorithm identifies auxiliary markets that correlate with the target market, fits appropriate models to predict future values, and then determines cloud confidence intervals around these predictions. Observations that deviate significantly from these intervals are flagged as potential signals, suggesting unexpected changes or trends in the target market. Our method not only enhances the ability to detect significant signals in financial markets but also provides a valuable tool for investors and analysts to anticipate and respond to market fluctuations, particularly during periods of economic instability, ultimately contributing to more informed decision-making and risk mitigation strategies.

Keywords

References

[1] S. Aliahmadi, M. Ahmadlou, Forecast the Gold coin future contracts prices by ARIMA models in Iran Mercantile Exchange (IME), Financial Knowledge of Securities Analysis 4 (2011) 61–74.
[2] E.M. Azoff, Neural Network Time Series Forecasting of Financial Markets, John Wiley & Sons, 1994.
[3] A. Babii, E. Ghysels, J. Striaukas, Machine learning time series regressions with an application to nowcasting, J. Bus. Econ. Stat. 40 (2022) 1094–1106.
[4] A. Blazquez-Garcia, A. Conde, U. Mori, J.A. Lozano, A review on outlier/anomaly detection in time series data, ACM Comput. Surv. 54 (2021) 56.
[5] S. Crepey, N. Lehdili, N. Madhar, M. Thomas, Anomaly detection in financial time series by principal component analysis and neural networks, Algorithms 15 (2022) 385.
[6] M. Dehghani, M. Mohammad, H. Ansari-Samani, Machine learning algorithms for time series in financial markets, J. Soft Comput. Inf. Technol. 8 (2019) 60–67.
[7] M. Ghanbarzadeh, M. Aminghafari, A novel wavelet artificial neural networks method to predict non-stationary time series, Commun. Stat. - Theor. Meth. 49 (2020) 864–878.
[8] M. Gupta, J. Gao, C.C. Aggarwal, J. Han, Outlier detection for temporal data: A survey, IEEE Trans. Knowl. Data Eng. 26 (2013) 2250–2267.
[9] R. Gupta, C. Pierdzioch, R. Selmi, M.E. Wohar, Does partisan conflict predict a reduction in US stock market (realized) volatility? Evidence from a quantile-on-quantile regression models, N. Am. J. Econ. Finance 43 (2018) 87–96.
[10] H. Hewamalage, C. Bergmeir, K. Bandara, Recurrent neural networks for time series forecasting: Current status and future directions, Int. J. Forecast. 37 (2021) 388–427.
[11] T. Hill, M. O’Connor, W. Remus, Neural network models for time series forecasts, Manage Sci. 42 (1996) 1082–1092.
[12] M. Holopainen, M. Toivonen, Weak signals: Ansoff today, Futures 44 (2012) 198–205.
[13] M. Jin, H.Y. Koh, Q. Wen, D. Zambon, C. Alippi, G.I. Webb, I. King, S. Pan, A survey on graph neural networks for time series: Forecasting, classification, imputation, and anomaly detection, IEEE Trans. Pattern Anal. Mach. Intell. 2024 (2024) 12.
[14] B. Kedem, K. Fokianos, Regression Models for Time Series Analysis, John Wiley & Sons, 2005.
[15] A. Mohammadi, H. Pashootanizadeh, Scenario planning the effect of foreign Gold price and exchange rate on financial market with using system dynamics approach, Journal of Financial Management Perspective 7 (2017) 27–50.
[16] C.W. Ostrom, Time Series Analysis: Regression Techniques, Sage, US, 1990.
[17] R.H. Shumway, D.S. Stoffer, Time Series Analysis and its Applications: With R Examples, Springer, 2011.
[18] X. Song, Y. Liu, L. Xue, J. Wang, J. Zhang, J. Wang, L. Jiang, Z. Cheng, Time-series well performance prediction based on long short-term memory (LSTM) neural network model, J. Pet. Sci. Eng. 186 (2020) 106682.
[19] L. Su, L. Deng, W. Zhu, S. Zhao, Statistical detection of weak pulse signal under chaotic noise based on Elman neural network, Wirel. Commun. Mob. Comput. 2020 (2020) 9653586.
[20] T. Su, R. Li, B. Liu, X. Liang, X. Yang, Y. Zhou, Anomaly detection and risk early warning system for financial time series based on the WaveLST-Trans model, ICCK Trans. Emerg. Top. Comput. Artif. Intell. 2 (2025) 68–80.
[21] Z. Tang, P.A. Fishwick, Feedforward neural nets as models for time series forecasting, ORSA J. Comput. 5 (1993) 374–385.
[22] R.S. Tsay, Analysis of Financial Time Series, John Wiley & Sons, 2010.
[23] Z. Zamanzadeh Darban, G.I. Webb, S. Pan, C. Aggarwal, M. Salehi, Deep learning for time series anomaly detection: A survey, ACM Comput. Surv. 57 (2024) 15.
[24] G.P. Zhang, M. Qi, Neural network forecasting for seasonal and trend time series, Eur. J. Oper. Res. 160 (2005) 501–514.
Journal of Mathematical Modeling
Volume 14, Issue 1
March 2026
Pages 93-114

Files

Share

How to cite

Statistics