پیش‌بینی بازده قرارداد آتی سکه طلا در بورس کالای ایران: با رویکرد مقایسه ای مدل آرچ و شبکه عصبی

نوع مقاله : علمی

نویسندگان

1 استاد گروه مدیریت بازرگانی، دانشکده علوم اقتصادی و اداری، دانشگاه مازندران، بابلسر، ایران.

2 استادیار گروه مدیریت بازرگانی، دانشکده علوم اقتصادی و اداری، دانشگاه مازندران، بابلسر، ایران.

3 کارشناس ارشد مدیریت بازرگانی گرایش مالی، دانشکده علوم اقتصادی و اداری، دانشگاه مازندران، بابلسر، ایران.

چکیده

با توجه به اهمیت و نقش طلا به‌عنوان ابزاری برای سرمایه‌گذاری، بخصوص در کشوهای درحال‌توسعه، روش‌های مختلفی برای پیش‌بینی بازده آتی طلا استفاده‌شده است. ازاین‌رو، هدف اصلی از پژوهش حاضر پیش‌بینی بازده روزانه قرارداد آتی سکه طلا در بورس کالای ایران با استفاده از مدل آرچ و شبکه عصبی است. برای این منظور، از داده-های روزانه 20 قرارداد آتی سکه طلا برای دوره زمانی تیرماه 1392 تا شهریورماه 1395 که به روش «تعدیل به عقب» پیوسته شده‌اند، به کار گرفته شد. همچنین پس از بررسی نتایج تحقیقات پیشین از بازده قیمتی دلار، بازده قیمتی سکه طلا و بازده قیمتی طلای جهانی به‌عنوان متغیرهای مؤثر بر بازده قرارداد آتی سکه طلا استفاده شد. علاوه بر این، دقت پیش‌بینی این مدل‌ها با استفاده از معیارهای میانگین مربعات خطا، ریشه میانگین مربعات خطا، میانگین قدر مطلق خطا و ضریب تعیین ارزیابی شد. نتایج پژوهش نشان داد در دوره موردبررسی، شبکه عصبی در مقایسه با مدل آرچ در پیش‌بینی برون نمونه بهتر عمل کرده است؛ اما بر مبنای نتایج آزمون تی زوجی، دقت پیش‌بینی دو مدل ازنظر آماری تفاوت معناداری نداشته است.

کلیدواژه‌ها


عنوان مقاله [English]

Forecasting of Gold Coin Future Contract Return in Iran Mercantile Exchange: with Approach of Comparative between ARCH Model and Neural Network

نویسندگان [English]

  • Mahmood Yahyazadehfar 1
  • Shahabeddin shams 2
  • aghdas fallah 3
1 Prof. in Department of Business Management, Faculty of Economics and Administrative Sciences, University of Mazandaran , Babolsar, Iran.
2 Assistant Prof. in Department of Business Management, Faculty of Economics and Administrative Sciences, University of Mazandaran, Babolsar, Iran.
3 MSc. student of Business Management, Faculty of Economics and Administrative Sciences, University of Mazandaran. Babolsar. Iran.
چکیده [English]

Given the importance and role of gold as a tool for investing, especially in developing countries, various approaches have been used to predict gold future returns. Hence, the main purpose of the present study is prediction the daily return of gold coin future contract by using multilayer feed-forward neural network and auto-regressive conditional heteroskedasticity (ARCH) models in Iran mercantile exchange. For this purpose, the daily data on 20 the gold coin futures contracts for periods July 2014 to September 2016 which has been continued using the method “back-adjusted”, is used. Also, after investigating results of previous studies, dollar price return, gold coin price return and global gold price return have been used as effecting variables on gold coin future contracts return. In addition, Predictive accuracy the neural network and the ARCH models were evaluated using root mean squared error (RMSE), mean squared error (MSE), mean absolute error (MAE) and coefficient of determination (R2). The results showed that in the period under review, the neural network model performs better than the ARCH model in the prediction out of sample. But based on the results of the paired t-test, the prediction accuracy of the two models hasn’t been the statistically significant difference.

کلیدواژه‌ها [English]

  • Forecasting of return
  • Gold coin future contract
  • Neural Network
  • ARCH model
  • Multiple linear regression
Bahrami, J., Mirzapour, A. & Fakari, B. (2014).  Hedging Through Gold Coin Futures Market Using Mean Extended Gini (MEG) Coefficient Approach: The Case of Iran Mercantile Exchange (IME). Financial Knowledge of Security Analysis, 7(21): 43-56.
Charef, F. & Ayachi, F. (2016). A Comparison between Neural Networks and GARCH Models in Exchange Rate Forecasting. International Journal of Academic Research in Accounting, Finance and Management Sciences, 6(1): 94-99.
Chaudhuri, T. D. & Ghosh, I. (2016). Artificial Neural Network and Time Series Modeling Based Approach to Forecasting the Exchange Rate in a Multivariate Framework. Journal of Insurance and Financial Management, 1(5): 92-123.
Fallah, J. & Ghaffari, F. (2015). The Effects of Margin Changes on the Futures Prices, Trading Volume and Price Volatility in Iran Mercantile Exchange Gold Coin Futures Contracts. Quarterly Journal of Economic Research and Policies, 23(73): 25-52.
Goodarzi, M. & Amiri, B. (2013). A Model on Identifying Affecting Factors of Azadi Gold Coin’s Futures Price, by Using Artificial Neural Network in Comparative of Multi-Regression Model. Financial Engineering and Securities Management, 4(15): 17-33.
Hull, J. (2002). Fundamentals of Futures and Options Markets. (A. Salehabadi, & S. Sayyah, Trans.) Tehran: TadbirPardaz IT Group.
Kocak, H. & Un, T. (2014). Forecasting the Gold Returns with Artificial Neural Network and Time Series. International Business Research, 7(11): 138-152.
Khosravinejad, A. A. & Shabani Sadr Pishe, M. (2014). An Evaluation of Linear and non-linear Models in Forecasting Stock Price Index in Tehran Stock Exchange. Financial Economics and Development, 8(27): 51-64.
Lovison, F. (2014). Technical Analysis Trading Strategy: An Application on Continuous Light Sweet Crude Oil WTI Futures Contract (@CL), Masaryk University, Economics and Administration.
Memarnejad, A. & Farmanara, V. (2011). Forecasting of Gold Coin Price in Iran Mercantile Exchange with Approach of Neural Network GMDH. Applied Economics, 2(6): 27-48.
Mombeini, H. & Yazdani-Chamzini, A. (2015). Modeling Gold Price via Artificial Neural Network. Journal of Economics, Business and Management. 3(7): 699-703.
Noroozpour Shahrbijari, M. & Moghaddam, A. (2015). Investigating of Factors Affecting in Gold Coin Futures Prices in Iran Mercantile Exchange. Intarnational Journal of Review in Life Sciences. 5(9): 93-99.
Pousti, F. & Salehi Sadaghiani, J. (2011). An Econometrics Method for Estimating Gold Coin Futures Prices. Management Science Letters, 1(11): 621-630.
Raei, R. & Saeedi, A. (2014). Fundamentals of financial Engineering and Risk Management. Tehran: Samt.
Raei, R., Honardoost, A., Salmani, Y. & Tataei, P. (2014). The Effect of Maturity Date, Trade Volume and Open Interests on Gold Coin Future Price Volatility. Journal of Investment Knowledge, 3(9): 169-185.
Souri, A. (2013). Econometrics, Tehran: Farhangshenasi.
Shams, SH. Golbabaie, A. & Dabirian, M. (2014). An Introduction to Financial Modeling Using Some Related Applications. Tehran: Termeh.
Saeedi, A. & Alimohammadi, SH. (2014). Exchange by Using GLS & GARCH Approaches. Financial Engineering and Securities Management, 5(20): 41-56.
Zarranejad, M. & Raoofi, A. (2015). Evaluation and Comparison of Forecast Performance of Linear and Non-linear Methods for Daily Returns of Tehran Stock Exchange. Financial Monetary Economics, 22(9): 1-29.