پیش‌بینی نرخ ارز با استفاده از الگوریتم‌های فراابتکاری

نوع مقاله : مقاله پژوهشی

نویسندگان

1 پژوهشگر اقتصاد کشاورزی، مؤسسه پژوهش‌های برنامه‌ریزی، اقتصاد کشاورزی و توسعه روستایی، تهران، ایران

2 دانشیار اقتصاد کشاورزی، مؤسسه پژوهش‌های برنامه‌ریزی، اقتصاد کشاورزی و توسعه روستایی، تهران، ایران

10.48308/jem.2025.237458.1952

چکیده

اتخاذ سیاست‌های نرخ ارز مناسب در کشورهای در حال توسعه، همواره بحث برانگیز است. سیاست‌گذاران پولی به منظور جلوگیری از زیان‌های ناشی از تغییرات نرخ ارز، درصدد یافتن روشی مناسب برای پیش‌بینی نرخ ارز بوده‌اند. حال آنکه ویژگی‌های سیاسی، اقتصادی نرخ ارز باعث رفتار پیچیده و غیرخطی آن شده و نشان از عملکرد بهتر این الگو‌ها در پیش‌بینی است. در این پژوهش با استفاده از الگوریتم‌های فراابتکاری الگوی بهینه نرخ ارز شبیه‌سازی شد. بدین منظور از 257 داده ماهانه نرخ ارز، نرخ تورم، قیمت نفتی سبد اوپک و نرخ سکه تمام بهار آزادی در بازه زمانی آذرماه 1379 لغایت اسفندماه 1400، استفاده گردید. ابتدا داده‌ها به دو دسته آموزش و آزمایش تقسیم شدند. هر یک از الگوریتم‌های فراابتکاری برای 24 ماه آینده از پارامترهای مربوط به هر الگوریتم اجرا شد. مقادیر ضرایب خطا، پس از رسیدن به ملاک توقف ثبت و نهایتا بهترین الگوریتم، بر اساس بیشترین همگرایی انتخاب شد. نتایج نشان داد الگوریتم ازدحام ذرات در تعداد و تکرار پایین همگرایی بسیار مطلوبی داشته و دارای عملکرد دقیق‌تری در پیش‌بینی نرخ ارز است. با توجه به این که الگوریتم‌های فراابتکاری قادر به بهینه‌سازی فرآیندهای مختلف مانند مدیریت زمان، منابع و تسهیل کردن برنامه ریزی روزانه هستند، پیشنهاد می‌شود سیاست‌گزاران از این الگوریتم جهت پیش‌بینی نرخ ارز استفاده کنند. 

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Forecasting the Exchange Rate Using Meta-Heuristic Algorithms

نویسندگان [English]

  • Fariba Abbasi 1
  • Ali Kiani Rad 2
1 Researcher in Agricultural Economics, Agricultural Planning, Economics and Rural Development Research Institute, Tehran, Iran
2 Associate Professor of Agricultural Economics, Agricultural Planning, Economics and Rural Development Research Institute, Tehran, Iran
چکیده [English]

Adopting appropriate exchange rate policies in developing countries is always controversial. In order to prevent losses from changes in exchange rates, monetary policymakers have always sought to find a suitable method for forecasting exchange rates. However, the political and economic characteristics of the exchange rate have caused complex and nonlinear behavior, indicating the use of better models in forecasting. In this study, the optimal exchange rate model was simulated using metaheuristic algorithms. For this purpose, from 257 monthly data of exchange rate, inflation rate, OPEC basket oil price and gold coin price during the period from December 2000 to March 2021, the data were first divided into two groups of training and testing. Each of the metaheuristic algorithms was run for the next 24 months with the parameters related to each algorithm. In each run, the value of the error coefficients was selected after reaching the stop criterion and finally the best algorithm was selected based on the highest convergence. The results show that the particle swarm algorithm had very good convergence in low number and iteration and had a more accurate performance in forecasting the exchange rate. Given that metaheuristic algorithms are capable of optimizing various processes such as time management, resources, and facilitating daily planning, this study suggests that policymakers use this algorithm to predict the exchange rate before planning in sectors.

کلیدواژه‌ها [English]

  • Unofficial Exchange Rate
  • Forecast
  • Meta-Heuristic Algorithm

مراجع

  • Abdollahi, A., & Khozin, A. (2016). Using genetic algorithm to optimize the Time-Cost-Quality-Risk in construction projects and investment plans. Accounting and Auditing Studies, 5(20), 104-123 (In Persian).
  • Babajani, J., Taghva, M., Blue, G., & Abdollahi, M. (2019). Forecasting Stock Prices in Tehran Stock Exchange Using Recurrent Neural Network Optimized by Artificial Bee Colony Algorithm. Journal of Financial Management Strategy, 7(2), 195-228 (In Persian).
  • Bafandeh Imandoust, S., Fahimifard. S. M., & Shirzady. S. (2010). Iran's Exchange Rate Forecasting Using ANFIS, NNARX & ARIMA Models (2002-2008). Monetary & Financial Economics, 16(28), (In Persian).
  • Bigi, R. & Salehi, M. (2012). The application of the cuckoo algorithm in predicting the bankruptcy of companies listed on the Tehran Stock Exchange. The 11th National Accounting Conference of Iran (In Persian).
  • Dashti, R., Sattari, M.T., & Nourani, V. (2017). Performance Evaluation of Differential Evolution Algorithm in Optimum Operating of Eleviyan Single-Reservoir Dam System. Journal of Water and Soil Resources Conservation, 3, 61-76 (In Persian).
  • Davoodi, P. & Zolghadri, M. (2012). The Study of Relationship between Interest Rate and Inflation in Iran. Journal of Economics and Modelling, 2(7-8), 1-25 (In Persian).
  • Ebrahim Khani, H., Kazemi, M., Pooya, A.R., & Fakoor Saghih, A.M. (2019). Prediction of Growth of Small and Medium Enterprises with the Combination of Artificial Neural Networks and Meta-Heuristic Algorithm. Modiriat-e- farad, 60, 205-220 (In Persian).
  • Emami Meibodi, , Amadeh, H., Memarzadeh, A., Ghasemi Nejad, A. (2013). Comparing the performance of GARCH Model and Gravitational Search Algorithm (GSA) in Modeling and Forecasting of Spot Oil Price of Iran (Adaptive Expectations Approach). Journal of Energy. 4(14), 1-23 (In Persian).
  • Golkar, F., Farahmand, A. R., Farahmand, F. (2008). Investigating the Application of Artificial Neural Network in Forecasting Precipitation in Shiraz Region. National Water Crisis Management Conference. SID. https://sid.ir/paper/809684/fa. (In Persian).
  • Eshghi, K., & Araghi, M. (2009). A Metaheuristic Algorithm for Stochastic Assignment Problem. Sharif Journal of Industrial Engineering & Management, 24(45), 3-12 (In Persian).
  • Jafari, A. A. Sadeghi Sarostani, A. & Mousavinejad, F. (2013). Presenting the anil simulation algorithm to solve the open routing problem of vehicles. The 15th Iranian Electrical Engineering Student Conference. 1-17 (In Persian).
  • Jalaee, S. A., Mir, H., & Rahimipoor, A. (2016). Effect of exchange rate pass on Stock Returns in Tehran Stock Exchange. Journal of Investment Knowledge, 5(19), 191-212 (In Persian).
  • Karaboga D., Basturk (2007). Advances in Soft Computing: Foundations of Fuzzy Logic and Soft Computing, Springer-Verlag, 4529, 31-36.
  • Khatib Semnani, M.A., Hadinejad, M., & Khashoui, R. (2014). Comparing the power of artificial neural network and dynamic neural network models in forecasting exchange rates: an application of wavelet transforms. Journal of Future Studies of Management, 100(25), 35-49 (In Persian).
  • Liben Nowell, D., & Kleinberg, J. (2007). The Link- Prediction Problem for Social Network. Journal of the American Society for Information Science and Technology, 58(7),1019-1031.
  • Moallem, P., Sadeghi, Hariri, M., & Hashemi, M. (2018). Modified Rrthogonal Chaotic Colonial Competition Algorithm and its Application in Improving Pattern Recognition in Multilayer Perceptron Neural Network. Journal of Information and Communication Technology, 35, 1-14 (In Persian).
  • Ri. & Kennedy. J. (2007). Blackwell Tim Particle swarm optimization an overview. Shlesinger Science, 33–57, Swarm Intel．
  • Pour Gharavi, Z. (2015). Harmony search algorithm to solve multi-objective optimization problems. Master's thesis in the field of applied mathematics, research orientation in operations. Shahroud University of Technology (In Persian).
  • Price, K.V., Storn, R.M. & Lampinen, J.A. (2005). Differential Evolution: A Practical Approach to Global Optimization. Springer.
  • Rajabioun, R. (2011). Cuckoo Optimization Algorithm. Applied Soft Computing, 11(8), 5508-5518.
  • Ramezani Muzirji, F., & Yaqoubi, M. (2008). Chiatic Algorithm for Bird Optimization. Iran National Software Engineering Conference. SID. https://sid.ir/paper/809357/fa. (In Persian).
  • Razavi, S.A., & Ahmadi Shadmehri, M.T. (2014). Investigating the Factors Influencing the Demand for Electricity in Service Providing Sector using Firefly and Cuckoo Algorithms. Journal of Economics and Modelling, 5(17-18), 111-134 (In Persian).
  • Rezaei, A. R., & Ranjbaran, S. (2013). Application Training of Genetic Algorithm in MATLAB Software. Azar Publications (In Persian).
  • Sadeghi, H., SohrabiVafa, H., Nouri, F. (2013). Combining Neural Networks and Evolutionary Algorithms on Energy Demand Prediction. Journal of Economic Policy, 6(11), 55-89 (In Persian).
  • Sepehri, M., Ildoromi, A.R., Hosseini, S.Z, Nori, H., Mohammadzade, F. & Artimani, M.M. (2018). The combination of neural networks and genetic algorithms is a way to estimate the Peak flood. Jwmseir, 11(39), 23-28.
  • Shahhosseini, S., & Rezaei, A. (2019). Forecasting of Iran’s Official Exchange Rate Using the Autoregressive ARIMA Intervention Model. new economy and trad, 13(4), 131-158 (In Persian).
  • Sherkat, E., Ehsan, Rahgozar, M., & Asadpour, M. (2013). Prediction of links in social networks using an optimization algorithm. The CSI Journal on Computer Science and Engineering, 12(1), 1-9 (In Persian).
  • Zare Mehrjardi, Y., Barki, Sh. & Momeni, J.A. (2018). Applying innovative method - simulation of gradual refrigeration to solve supply chain problems. Journal of Operational Research in its Applications (Applied Mathematics), 8(3(30)), 1-24 (In Persian).

فایل ها

هم رسانی

ارجاع به این مقاله

آمار