Agricultural Economics

Agricultural Economics

به‌کارگیری یادگیری ماشین در تحلیل اثرپذیری شاخص صنایع غذایی: شبکه عصبی حافظه طولانی کوتاه‌مدت (LSTM)

نوع مقاله : مقاله پژوهشی

نویسندگان
1 دانش‌آموخته‌ کارشناسی ارشد، گروه اقتصاد کشاورزی، دانشکده مهندسی زراعی، دانشگاه علوم کشاورزی و منابع طبیعی ساری، مازندران، ایران
2 گروه اقتصاد کشاورزی- دانشگاه علوم کشاورزی و منابع طبیعی ساری
3 استاد، گروه اقتصاد کشاورزی، دانشکده مهندسی زراعی، دانشگاه علوم کشاورزی و منابع طبیعی ساری، مازندران، ایران
4 دانشجوی دکتری، گروه اقتصاد کشاورزی، دانشکده مهندسی زراعی، دانشگاه علوم کشاورزی و منابع طبیعی ساری، مازندران، ایران
10.22034/iaes.2025.2058957.2124
چکیده
این پژوهش باهدف تحلیل اثرپذیری شاخص صنایع غذایی از بازارهای مالی منتخب ایران شامل شاخص کل بورس، نرخ ارز و قیمت سکه، با بهره‌گیری از مدل شبکه عصبی حافظه بلندمدت کوتاه‌مدت (LSTM) انجام شده است. صنایع غذایی، به‌عنوان یکی از ارکان اقتصاد کشور، به‌شدت تحت‌تأثیر تحولات کلان اقتصادی و مالی قرار دارد و بررسی پویایی آن می‌تواند به شناسایی ساختارهای میان بازاری و نحوه سرایت نوسانات کمک کند. در این راستا، داده‌های سری زمانی مربوط به دوره فروردین ۱۳۹۶ تا اسفند ۱۴۰۲ برای مدل‌سازی مورد استفاده قرار گرفت. مدل LSTM با توانایی شناسایی الگوهای غیرخطی و وابستگی‌های زمانی پیچیده، در پیش‌بینی هم‌زمان سطح و نوسانات متغیرهای مورد بررسی به کار گرفته شد. نتایج نشان داد که شاخص صنایع غذایی بیشترین همبستگی را با شاخص کل بورس دارد و ارتباط آن با نرخ ارز و قیمت سکه، به‌ویژه در سطح قیمت‌ها، ضعیف‌تر است. در سطح نوسانات نیز همبستگی‌ها میان بازارها افزایش می‌یابد که بیانگر اهمیت شوک‌های کوتاه‌مدت در رفتار بازارهاست. ارزیابی مدل LSTM بر اساس شاخص‌های خطای آماری مانند MSE و MAE نشان داد که این مدل قادر به بازتولید دقیق رفتار متغیرهاست و از پایداری مناسبی برخوردار است. همچنین، تفاوت معنادار میان همبستگی‌های سطح قیمت و نوسانات، لزوم تحلیل هم‌زمان این دو بُعد را در مطالعات بازارهای مالی برجسته می‌سازد. یافته‌های این پژوهش تصویری جامع از ساختار پویای اثرگذاری متقابل بازارها ارائه می‌دهد و کارایی بالای LSTM را در تحلیل پیش‌بینانه سری‌های مالی نشان می‌دهد.
کلیدواژه‌ها
موضوعات

Adams, S. and Uchema, J. (2024) Nigeria Exchange Rate Volatility: A Comparative Study of Recurrent Neural Network LSTM and Exponential Generalized Autoregressive Conditional Heteroskedasticity Models. Journal of Artificial Intelligence and Big Data, 4: 61-73. 
Adibpour, M. (2017) Measuring the Effect of Exchange Rate Uncertainty on Industrial Corporates Stock Price Index of Tehran Stock Exchange. Macroeconomics Research Letter, 11(22): 105-131. (In Persian) 
Agarwal, S., Sharma, S., Faisal, K. and Sharma, R. (2025) Time-Series Forecasting Using SVMD-LSTM: A Hybrid Approach for Stock Market Prediction. Journal of Probability and Statistics, 2025: 1-14. 
Aghaei, M., Rezagholizadeh, M. and Chawshany, S. (2024) Investigation the Spillover of Volatility and Return Between Cross-Border Markets (Forex and Cryptocurrencies) and Stock Market in Iran. Journal of Economics and Modelling, 14(4): 113-160. (In Persian) 
Andersen, T. G., and Bollerslev, T. (1997) Heterogeneous Information Arrivals and Return Volatility Dynamics: Uncovering the Long-run in High Frequency Returns. Journal of Finance, 52: 975-1005.
Azarm, H., Farajzadeh, Z. (2022) Challenges and opportunities of investment and financing to improve agricultural production. Journal of Agricultural Production and Marketing Economics, 1(1): 5-24. (In Persian)
Beheshti Masalegou, M., Afshar Kazemi, M. A., Haghighat Monfared, J. and Rezaeian, A. (2023) Deep learning for stock market forecasting using numerical and textual information (Long-Short Term Memory approach). Quarterly Financial Engineering and Securities Management, 14(55): 65-87. (In Persian)
Bhandari, H., Rimal, B., Pokhrel, N., Rimal, R., Dahal, K. and K C Khatri, R. (2022) Predicting stock market index using LSTM. Machine Learning with Applications, 9: 1-15. 
Bhanuse, P., Bansode, P. and Pukale, P. (2023) Stock Market Prediction Model using LSTM. International Journal for Research in Applied Science and Engineering Technology, 11: 503-507. 
Bollerslev, T. (1986) Generalized Autoregressive Conditional Heteroskedasticity. Journal of Econometrics, 31(3): 307-327.
Botunac, I., Bosna, J. and Matetic, M. (2024) Optimization of Traditional Stock Market Strategies Using the LSTM Hybrid Approach. Information, 15:1-17. 
Cao, J., Li, Z. and Li, J. (2018) Financial time series forecasting model based on CEEMDAN and LSTM. hysica A: Statistical Mechanics and its Applications, 519: 127-139. 
Cheteni., P. (2017) Stock market volatility using GARCH models: Evidence from South Africa and China stock markets. Journal of Economics and Behavioral Studies, 8: 237-245. 
Chkili, W. and Nguyen, D.K. (2014) Exchange rate movements and stock market returns in a regime-switching environment: Evidence for BRICS countries. Research in International Business and Finance, 31: 46-56.
Doostian, R. and Mirashrafi, Z. (2025) Evaluating volatility of markets parallel to the money market on return of the capital market banking industry. International Journal of Finance & Managerial Accounting, 10(39): 233-243.
Dourandish, A., Shariat, E. and Arzande, N. (2014) The Study of Volatility Spillover Effects of The Exchange Rate on Agricultural Industry Index Listed on The Stock Exchange. Journal of Agricultural Economics and Development, 28(2): 177-184. (In Persian)
Engle, R.F. (1982) Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation. Econometrica, 50(4): 987-1007.
García-Medina, A. and Moreno, E. (2023) STM–GARCH Hybrid Model for the Prediction of Volatility in Cryptocurrency Portfolios. Computational Economics, 63: 1511-1542.
Hansen, J. V., McDonald, J. B. and Nelson, R. D.  (1999) Time series prediction with genetic-algorithm designed neural networks: An empirical comparison with modern statistical models. Computational Intelligence, 15(3): 171-184. 
Hochreiter, S. and Schmidhuber, J. (1997) Long Short-Term Memory. Neural Computation, 9(8): 1735-1780. 
Jahangiri, K. and Hoseini Ebrahimabad, A. (2017) The Study of Monetary Policy, Exchange Rate and Gold Effects on the Stock Market in Iran Using MS-VAR-EGARCH Model. Financial Research Journal, 19(3): 389-414. (In Persian)
Kazemi, S. (2012) A review of econometric methods and applications. First International Conference on Econometrics, Methods and Applications, 1-23. (In Persian)
Keshavarzhaddad, G., Ebrahimi, B. and Jafar Abdi, A. (2011) Investigating the contagion of volatility between stock returns of the cement industry and its related industries in Iran. Iranian Quarterly Journal of Economic Research, 16(47): 129-162. (In Persian)
Kim, H. and Won, C. (2018) Forecasting the Volatility of Stock Price Index: A Hybrid Model Integrating LSTM with Multiple GARCH-Type Models. Expert Systems with Applications, 103: 25-37. 
Liu, Y. (2019) Novel Volatility Forecasting Using Deep Learning – Long ShortTerm Memory Recurrent Neural Networks. Expert Systems with Applications,132: 99- 109.
Mohammadi, T., Ghasemi, A. Taklif, A. and Sadeghin, A. (2021) The analysis of permanent and temporary fluctuations of Brent Oil & Relative Industries Index With Gold, Currency Index: Network Approach. Financial Economics, 15(56): 89-115. (In Persian) 
Nikou, M.,  Mansourfar, G. and Bagherzadeh, J. (2019) Stock price prediction using DEEP learning algorithm and its comparison with machine learning algorithms. Intelligent Systems in Accounting, Finance and Management, 26: 164-174. 
Praneeth, M.V., Rahman, M.U. and Sharma, K.V. (2024) Adaptive Stock Market Prediction Using LSTM and Sentiment Analysis for Volatile Market Conditions. Frontiers in Collaborative Research, 2(2): 14-24.
Qu, Y. and Zhao, X. (2019) Application of LSTM Neural Network in Forecasting Foreign Exchange Price. Journal of Physics: Conference Series, 1237: 1-5. 
Rameh, T., Abbasi, R. and Sanai, M. R. (2022) Forecasting the stock market using LSTM neural network hybrid model. Knowledge publishing platform, 1-21. (In Persian)
Rezaei, M. and Ahmadi, A. (2024) Analyzing Financial Risk Prediction Using Deep Learning Algorithms: A Comparative Study of LSTM and CNN Models. Accounting, Finance and Computational Intelligence, 1(1): 1-12. (In Persian)
Sadeghi shahdani, M, and Mohseni, H. (2018) Spillover and transfers of gold coin price fluctuations on the capital market. Financial Economics, 12(44): 103-121. (In Persian)
Securities & Exchange Organization. (2019) <www.seo.ir>.
Selvin, S., Ravi, V., Gopalakrishnan, E. A., Menon, V. K. and Soman, K. P. (2017) Stock price prediction using LSTM, RNN and CNN-sliding window model. Proc. Int. Conf. Advances in Computing, Communications and Informatics (ICACCI), Udupi, India. 
Shahrabi Ameri, H. and Taiebysani, E. (2025) Evaluation of the performance of recursive neural network (RNN) Long-Short Term Memory (LSTM) method in stock price forecasting. Journal of Investment Knowledge, 14(55): 93-117. (In Persian)
Shaki, S. and Tofighi, H. (2012) The effect of exchange rate fluctuations on Iranian stock market returns. The Second National Conference on Regionally Oriented Economic Development Strategies, 1-18. (In Persian) 
Shapiro, D. (2022) Identification of structural multivariate GARCH models. Journal of Econometrics, 227(1): 212-227.
Shariffar, A., Khalili Araghi, M., Raeesi Vanani, I. and Fallah, M. (2021) The Assessment of the optimal Deep Learning Algorithm on Stock Price Prediction (Long Short-Term Memory Approach). Financial Engineering, 12(48): 348-370. (In Persian)
Shinagawa, Y. (2014) Determinants of Financial Market Spillovers: The Role of Portfolio Diversification, Trade, Home Bias, and Concentration. IMF Working Papers, 14:1-24. 
Taheri, S., Abdul Baqi Attaabadi, A. M., Waziri Sarshak, M. and Arman, M. H. (2023) The Effect of Gold and Exchange Rate Volatility on Capital Market Volatility. Financial Economics, 17(63): 95-116. (In Persian)
Tule, M., Dogo, M. and Uzonwanne, G. (2018) Volatility of stock market returns and the naira exchange rate. Global Finance Journal, 35: 97-105.
Zaremba, W., Sutskever, I. and Vinyals, O. (2014) Recurrent neural network regularization. arXiv preprint arXiv:1409.2329.
Ziyadi, H., Salavati, E. and Lotfi Heravi, M. (2023) Housing Price Forecasting Using AI (LSTM). Financial Research Journal, 25(4): 557-576. (In Persian)
Zoghi, S., Raei, R. and Falahpor, S. (2022) Presenting a market direction prediction model for gold coin trades in Iran’s Commodity Exchange market using Long Short-Term Memory (LSTM) algorithm. Financial Engineering and Portfolio Management, 13(53): 34-53. (In Persian)