بهبود دقت پیش‌بینی نرخ رشد اقتصادی با استفاده از ترکیب تبدیل موجک و شبکه عصبی مصنوعی

کرمی, بهاره; کیان پور, سعید

doi:10.22034/jepr.2024.142083.1171

بهبود دقت پیش‌بینی نرخ رشد اقتصادی با استفاده از ترکیب تبدیل موجک و شبکه عصبی مصنوعی

نوع مقاله : پژوهشی

نویسندگان

¹ دکتری اقتصاد بخش عمومی، حسابرس اداره امور مالیاتی استان کردستان، سنندج، ایران.

² استادیار، گروه اقتصاد، دانشگاه پیام نور، تهران، ایران.

10.22034/jepr.2024.142083.1171

چکیده

پیش‌بینی رفتار متغیرهای کلان و مالی اقتصاد برای سیاست‌گذاران از اهمیت بالایی برخوردار است. این امر برای اقتصادهای در حال توسعه از جمله ایران یک کار چالش برانگیز است زیرا مجموعه‌ای از عواملی که در تئوری‌های اصلی اقتصاد در نظر گرفته نشده‌اند، اغلب نقش مهمی در شکل دادن به محیط و چشم‌انداز کلی اقتصاد آنان دارد. روابط اقتصادی در این نوع محیط‌ها بی‌ثبات‌تر و همراه با روند غیرخطی‌ است. ترکیب تبدیل موجک و شبکه عصبی مصنوعی یک تحلیل مدل‌سازی ریاضی نوظهور در سال‌های اخیر است که به منظور نویز‌زدایی در سری‌های زمانی و افزایش دقت پیش‌بینی پیشنهاد شده است. در این پژوهش تلاش شد با استفاده از ترکیب تبدیل موجک و شبکه عصبی مصنوعی، مدلی به منظور پیش‌بینی رشد اقتصادی ایران ارائه گردد تا دقت پیش‌بینی روش ترکیبی با شبکه عصبی مصنوعی مقایسه شود. نتاﯾﺞ مطالعه ﺑﻬﺒﻮد ﻣﻌﻨﺎدار در پیش‌بینی شبکه عصبی ﺑﺎ اﺳﺘﻔﺎده از دادهﻫﺎی نویز‌زدایی شده را نشان داد. نتایج همچنین برتری مدل ترکیبی را نسبت به مدل‌های XGBoost و ARIMA تأیید کرد. دقت پیش‌بینی این مدل‌ها بر اساس معیارهایی مانند ریشه میانگین مربع خطا و آزمون دیبولد_ماریانو ارزیابی و مقایسه شده است.

کلیدواژه‌ها

موضوعات

مراجع

Abbasi Nejad, H., & Mohammadi, A. (2007). Forecasting exchange rate using neural networks and wavelet transform. The Journal of Economic Studies and Policies, 0(11), 19-42. https://economic.mofidu.ac.ir/article_47088.html?lang=en [In Persian]

Al Wadia, M. T. I. S., & Ismail, M. T. (2011). Selecting wavelet transforms model in forecasting financial time series data based on ARIMA model. Applied Mathematical Sciences, 5(7), 315-326. (URL of Article)

Alexandridis, A. K., & Zapranis, A. D. (2013). Wavelet neural networks: A practical guide. Neural Networks, 42, 1-27. https://doi.org/10.1016/j.neunet.2013.01.008

Billings, S. A., & Wei, H. L. (2005). A new class of wavelet networks for nonlinear system identification. IEEE Transactions on neural networks, 16(4), 862-874. https://doi.org/10.1109/TNN.2005.849842

Cao, L., Hong, Y., Fang, H., & He, G. (1995). Predicting chaotic time series with wavelet networks. Physica D: Nonlinear Phenomena, 85(1-2), 225-238. https://doi.org/10.1016/0167-2789(95)00119-O

Chaudhary, S., & Uprety, D. (2023). Hybrids ARIMA-ANN models for GDP forecasting in Nepal. NRB Working Paper No. 56. (URL of Article)

Chuku, C., Simpasa, A., & Oduor, J. (2019). Intelligent forecasting of economic growth for developing economies. International Economics, 159, 74-93. https://doi.org/10.1016/j.inteco.2019.06.001

Clements, M., & Hendry, D. (2002). An overview of economic forecasting. A Companion to Economic Forecasting. Oxford: Blackwell, 1-18. https://doi.org/10.1002/9780470996430

Cody, M. A. (1994). The wavelet packet transform: Extending the wavelet transform. Dr. Dobb's Journal, 19, 44-46. (URL of Article)

Conlon, T., Crane, M., & Ruskin, H. J. (2008). Wavelet multiscale analysis for hedge funds: Scaling and strategies. Physica A: Statistical Mechanics and its Applications, 387(21), 5197-5204. https://doi.org/10.1016/j.physa.2008.05.046

da Costa, K. V. S., da Silva, F. L. C., & da Silva Cordeiro, J. (2021). Time Series Models Combination for Forecasting Quarterly GDP Components by the Expenditure Side. Trabalho apresentado em Anais do LIII Simpósio Brasileiro de Pesquisa Operacional. http://dx.doi.org/10.59254/sbpo-2021-131469

Debnath, L., & Shah, F. (2017). Lecture notes on wavelet transforms. Springer. https://doi.org/10.1007/978-3-319-59433-0

Fang, Y., & Chow, T. W. (2006, May). Wavelets based neural network for function approximation. In International symposium on neural networks (pp. 80-85). Berlin, Heidelberg: Springer Berlin Heidelberg. https://doi.org/10.1007/11759966_12

Feng, L., & Zhang, J. (2014). Application of artificial neural networks in tendency forecasting of economic growth. Economic Modelling, 40, 76-80. https://doi.org/10.1016/j.econmod.2014.03.024

Ghadimi, M. R., & Moshiri, S. (2002). Modeling and forecasting economic growth in Iran using artificial neural networks (ANN). Iranian Economic Research, 4(12), 97-125. (URL of Article) [In Persian]

Hakimipour, N., Faramarzi, A., & Askari, A. (2019). Predicting non-oil economic growth in Iran by economic sectors using the adaptive neuro-fuzzy inference system (ANFIS). Journal of Quantitative Economics, 16(1), 25-48. https://doi.org/10.22055/jqe.2019.22217.1644 [In Persian].

HameedAshour, M. A., & Ahmed, A. S. (2024, August). Forecasting Iraqi GDP Using Artificial Intelligence. In 2024 IEEE 15th Control and System Graduate Research Colloquium (ICSGRC) (pp. 97-101). IEEE. https://doi.org/10.1109/ICSGRC62081.2024.10691310

Hashemi Dizaj, H., Hazari Niri, H., & Pourvahdani. (2020). Comparing the performance of artificial neural network models for forecasting exchange rates in Iran. Semi-annual Journal of Economic Studies and Policies, 7(2), 53-80. https://doi.org/10.22096/esp.2020.43397 [In Persian].

Hawkins, J. (2005). Economic forecasting: history and procedures. Economic Round-up, (Autumn 2005), 1-10 (URL of Article)

Heravi, S., Osborn, D. R., & Birchenhall, C. R. (2004). Linear versus neural network forecasts for European industrial production series. International Journal of forecasting, 20(3), 435-446. https://doi.org/10.1016/S0169-2070(03)00062-1

Isa, N. M., & Shabri, A. (2013, September). A hybrid group method of data handling with discrete wavelet transform for GDP forecasting. In AIP Conference Proceedings (Vol. 1557, No. 1, pp. 566-570). American Institute of Physics. https://doi.org/10.1063/1.4823978

Jahn, M. (2018). Artificial neural network regression models: Predicting GDP growth (No. 185). HWWI Research Paper. https://hdl.handle.net/10419/182108

Jordan, M. I., & Mitchell, T. M. (2015). Machine learning: Trends, perspectives, and prospects. Science, 349(6245), 255-260. https://doi.org/10.1126/science.aaa8415

Khayamian, T., Ensafi, A. A., Tabaraki, R., & Esteki, M. (2005). Principal Component‐Wavelet Neural Networks as a New Multivariate Calibration Method. Analytical Letters, 38(9), 1477-1489. https://doi.org/10.1081/AL-200062265

Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. 3rd International Conference for Learning Representations (ICLR), San Diego. arXiv. https://doi.org/10.48550/arXiv.1412.6980

Kuan, C. M., & White, H. (1994). Artificial neural networks: An econometric perspective. Econometric reviews, 13(1), 1-91. https://doi.org/10.1080/07474939408800273

Logubayom, I. A., Nasiru, S., & Luguterah, A. (2013). Modelling the rate of treasury bills in Ghana. Mathematical Theory and Modeling, 3(4). (URL of Article)

Maasoumi, E., Khotanzed, A., & Abaye, A. (1994). Artificial neural networks for some macroeconomic series: a first report. Econometric Reviews, 13(1), 105-122. https://doi.org/10.1080/07474939408800276

Matta, C., Bianchesi, N., Oliveira, M., Balestrassi, P., & Leal, F. (2021). A comparative study of forecasting methods using real-life econometric series data. Production, 31, e20210043. http://dx.doi.org/10.1590/0103-6513.20210043

Mohammadi, T., Taklif, Z., & Sahel. (2017). Forecasting natural gas prices using a hybrid model of wavelet transform and artificial neural network (Case study: U.S. market). Iranian Economic Research, 22(71), 1-26. https://doi.org/10.22054/ijer.2017.8277 [In Persian]

Nason, G. P., & Sachs, R. V. (1999). Wavelets in time-series analysis. Philosophical transactions of the royal society of London. Series A: Mathematical, Physical and Engineering Sciences, 357(1760), 2511-2526. https://doi.org/10.1098/rsta.1999.0445

Nelson, C. R., & Plosser, C. R. (1982). Trends and random walks in macroeconmic time series: some evidence and implications. Journal of monetary economics, 10(2), 139-162. https://doi.org/10.1016/0304-3932(82)90012-5

Perron, P. (1989). The great crash, the oil price shock, and the unit root hypothesis. Econometrica: journal of the Econometric Society, 1361-1401. https://doi.org/10.2307/1913712

Raei, R., Mohammadi, S., & Fandreski, H. (2015). Predicting stock price index using neural network and wavelet transform. Asset Management and Financing, 3(1), 55-74. https://dor.isc.ac/dor/20.1001.1.23831170.1394.3.1.4.4 [In Persian]

Rostan, P., & Rostan, A. (2018). Forecasting Spanish GDPs with spectral analysis. Studies of Applied Economics, 36(1), 217-234. https://doi.org/10.25115/eea.v36i1.2526

Salehi Sarbijan, M. (2016). Modeling and forecasting Iran's economic growth using ARIMA, Markov-switching, and ANFIS models. Growth and Economic Development Research, 6(24), 55-68. https://dor.isc.ac/dor/20.1001.1.22285954.1395.6.24.3.2 [In Persian].

Shabri, A., & Samsudin, R. (2014). Daily crude oil price forecasting using hybridizing wavelet and artificial neural network model. Mathematical Problems in Engineering, 2014(1), 201402. https://doi.org/10.1155/2014/201402

Shafil, I., Ahmad, J., Shah, S. I., Mieee, S., & Kashif, F. M. (2006). Impact of varying neurons and hidden layers in neural network architecture for a time frequency application. 2006 IEEE International Multitopic Conference. https://doi.org/10.1109/INMIC.2006.358160

Shaygani, B., Salami, A. B., & Khuchiani, R. (2015). The Proposed Model for Prediction of GDP Using With ARIMA, Neural Networks and Wavelet Transform. Financial Knowledge and Securities Analysis, 7(24), 147-162. https://sanad.iau.ir/Journal/jfksa/Article/803494 [In Persian]

Subasi, A., Alkan, A., Koklukaya, E., & Kiymik, M. K. (2005). Wavelet neural network classification of EEG signals by using AR model with MLE preprocessing. Neural networks, 18(7), 985-997. https://doi.org/10.1016/j.neunet.2005.01.006

Tej, M. L., & Holban, S. (2018). Determining optimal neural network architecture using regression methods. 2018 International Conference on Development and Application Systems (DAS). https://doi.org/10.1109/DAAS.2018.8396093

Tkacz, G. (2001). Neural network forecasting of Canadian GDP growth. International Journal of Forecasting, 17(1), 57-69. https://doi.org/10.1016/S0169-2070(00)00063-7

Tümer, A. E., & Akkuş, A. (2018). Forecasting gross domestic product per capita using artificial neural networks with non-economical parameters. Physica A: Statistical Mechanics and its Applications, 512, 468-473. https://doi.org/10.1016/j.physa.2018.08.047

Türsoy, T. (2013). Forecasting Economic Growth Rate: The Case of North Cyprus. Journal of Social Sciences, 6(1), 193-20. https://www.researchgate.net/publication/260647374_Forecasting_Economic_Growth_Rate_the_Case_of_North_Cyprus

Uzair, M., & Jamil, N. (2020). Effects of hidden layers on the efficiency of neural networks. 2020 IEEE 23rd International Multitopic Conference (INMIC). https://doi.org/10.1109/INMIC50486.2020.9318195

Vogl, M., Rötzel, P. G., & Homes, S. (2022). Forecasting performance of wavelet neural networks and other neural network topologies: A comparative study based on financial market data sets. Machine Learning with Applications, 8, 100302. https://doi.org/10.1016/j.mlwa.2022.100302

Yu, Y. (2009). Evaluation of wavelet neural network for predicting financial market crisis. In 2009 First International Conference on Information Science and Engineering (pp. 4861-4864). IEEE. https://doi.org/10.1109/ICISE.2009.567

Zhang, G. P., & Qi, M. (2005). Neural network forecasting for seasonal and trend time series. European journal of operational research, 160(2), 501-514. https://doi.org/10.1016/j.ejor.2003.08.037

Zhang, Q. (1993). Regressor Selection and Wavelet Network Construction. Proceedings of 32nd IEEE Conference on Decision and Control, San Antonio, TX, USA, 1993, pp. 3688-3693 vol.4 https://doi.org/10.1109/CDC.1993.325905

Zhang, Q., & Benveniste, A. (1992). Wavelet networks. IEEE transactions on Neural Networks, 3(6), 889-898. https://doi.org/10.1109/72.165591

Zhang, Y., Shang, W., Zhang, N., Pan, X., & Huang, B. (2023). Quarterly GDP forecast based on coupled economic and energy feature WA-LSTM model. Frontiers in Energy Research, 11, 1329376. https://doi.org/10.3389/fenrg.2023.1329376