Zaman Serisi Verilerinde KullanÕlan Tahmin Tekniklerinin Veri Özelliklerine Göre Belirlenmesi ve KarúÕlaútÕrÕlmasÕ: BøST-100 Endeksi Üzerine Uygulama

Literatürde birçok tahmin tekni÷i yer almasÕna ra÷men en temel tahmin teknikleri hareketli ortalamalar, üstel düzeltme, ileri düzey üstel düzeltme tahmin teknikleri ve Pegels’in sÕnÕflandÕrma yöntemidir. Toplamda 18 farklÕ yöntemden oluúan bu temel tekniklerin hepsi için hesaplamalar yapmak oldukça zor ve zaman alÕcÕdÕr. Bu nedenle, çalÕúmada 2005 – 2017 arasÕndaki yÕllÕk ve 2010 Ocak – 2018 Nisan arasÕndaki aylÕk BøST-100 tüm endeks ortalama de÷erlerinin trend ve mevsimlik bileúenleri incelenmiú ve temel tahmin tekniklerinden 6 tanesine göre tahminler yapÕlmÕútÕr. Sonuç olarak zaman serisinin bileúenlerine göre öncelikle tahmin tekniklerinin belirlenmesinin hem zaman olarak hem de hesaplama açÕsÕndan karar vericilere olumlu katkÕ sa÷layaca÷ÕnÕ söylemek mümkündür.

Determination and Comparison of Forecasting Methods Used in Time Series by Data Features: An Application on BIST 100 Index

Although there are many forecasting methods in the literature, the most basic ones are moving averages, exponential smoothing methods, advanced exponential smoothing methods and Pegel’s classification method. It is difficult and time-consuming to calculate for all of these basic methods, which consist of a total of 18 different methods. Thus, in this paper, the trend and seasonal components of BIST-100 index between 2005 and 2017 as annually and between January 2010 and April 2018 as monthly average were analyzed and forcested based on 6 of these basic forecasting methods. As a result, it is possible to say that determination of forecasting methods firstly according to the components of time series will contribute positively to decision makers in terms of both time and calculation

___

  • Akgül, I. (2003). Geleneksel Zaman Serisi Yöntemleri. Der YayÕnevi, østanbul.
  • Anderson, D.R., Sweeney, D.J., Williams, T.A. ve Martin, K. (2008). An Introduction To Management Science Quantitive Approaches To Decision Making. 20.BaskÕ, Thomson South-Western Inc, Kanada.
  • Armutlulu, ø.H. (2008). øúletmelerde UygulamalÕ østatistik. 2.BaskÕ, Alfa BasÕm YayÕm Da÷ÕtÕm, østanbul. Athanasopoulos, G., Hyndman, R. J., Song, H. ve Wu, D. C. (2011). The Tourism Forecasting Competition. International Journal of Forecasting, 27, 822 – 844.
  • AydÕn, A.D ve Cavdar, ù.Ç. (2015). Comparison of Prediction Performances of Artificial Neural Network (ANN) and Vector Autoregressive (VAR) Models by Using the Macroeconomic Variables of Gold Prices, Borsa Istanbul (BIST) 100 Index and US Dollar-Turkish Lira (USD/TRY) Exchange Rates. Procedia Economics and Finance, 30, 3 – 14.
  • Borsa İstanbul, http://www.borsaistanbul.com/docs/default-source/endeksler/BIST-pay-endeksleri- temel-kurallari.pdf?sfvrsn=10 E.T: 21.06.2018.
  • BoyacÕo÷lu, M.A. ve AvcÕ, D. (2010). An Adaptive Network-Based Fuzzy Inference System (ANFIS) For The Prediction Of Stock Market Return: The Case Of The Istanbul Stock Exchange. Expert Systems with Applications, 37(12), 7908–7912.
  • Chen, A., Leung, M.T., Daouk, H. (2003). Application Of Neural Networks To An Emerging Financial Market: Forecasting And Trading The Taiwan Stock Index. Computers and Operations Research, 30, 901-923.
  • Cook, T.M. ve Russell, R.A. (1981). Introduction To Management Science. 2.BaskÕ, Prentice/Hall Inc, United States of America.
  • Çekerol, G.S. ve Ulukan, A. (2012). Kantitatif Tahmin Yöntemleri. Nisan Kitabevi, Ankara. Çekici, M. E. ve ønel, M. N. (2013). Türk Sigorta Sektörünün Direkt Prim Üretimlerinin Tahmin Teknikleri øle øncelenmesi. Marmara Üniversitesi øktisadi ve ødari Bilimler Dergisi, 34 (1), 135 – 152.
  • Çuhadar, M. (2014). Mu÷la øline Yönelik DÕú Turizm Talebinin Modellenmesi ve 2012 – 2013 YÕllarÕ øçin Tahminlenmesi. UluslararasÕ øktisadi ve ødari øncelemeler Dergisi, 12, 1 – 22.
  • Grubb, H. ve Mason, A. (2001). Long Lead-Time Forecasting of UK Air Passengers By Holt–Winters Methods With Damped Trend. International Journal of Forecasting, 17, 71 – 82.
  • Gündüz, H. ve Çataltepe, Z. (2013). Prediction of østanbul Stock Exchange (ISE) Direction Based on News Articles. Conference: The Third International Conference on Digital Information Processing and Communications (ICDIPC2013). January 30 – February 1 2013, Dubai, 320 – 330.
  • Hanke, J. E. ve Wichern, D. (2014). Business Forecasting. 9. BaskÕ, Pearson Education Limited, United State of America.
  • Li, X. (2013). Comparison And Analysis Between Holt Exponential Smoothing And Brown Exponential Smoothing Used For Freight Turnover Forecasts. Proceedings of the 2013 Third International Conference on Intelligent System Design and Engineering Applications. 16-18 January 2013, Hong Kong, China, 453 – 456.
  • Maçaira, P. M., Souza, R.C. ve Oliveira, C. (2015). Modelling and Forecasting the Residential Electricity Consumption in Brazil with Pegels Exponential Smoothing Techniques. Procedia Computer Science, 55, 328 – 335.
  • Makridakis, S., Wheelwright, S. C. ve Hyndman, R. J. (1998). Forecasting: Methods And Applications. 3. BaskÕ, John Wiley & Sons. Inc, United State of America.
  • Meesad, P. ve Srikhacha, T. (2006). Adaptive Approach and Seasonal Technique for Universal Data Forecasting. Proceeding of the 2006 International Conference on Computational Inteligence fo Modelling Control and Automation and International Conference on Intelligent Agents Web Technologies and International Commerce (CIMCA'06). 28 November – 1 December 2006, Vienna, Austria, 65 – 70.
  • ÖzçalÕcÕ, M. (2016). Yapay Sinir A÷larÕ øle Çok AúamalÕ Fiyat Tahmini: BøST30 Senetleri Üzerine Bir AraútÕrma. Dokuz Eylül Üniversitesi øktisadi ve ødari Bilimler Dergisi, 31 (2), 209 – 227.
  • Pegels, C.C. (1969). Exponential Forecasting: Some New Variations. Management Science, 15 (5), 311 – 315.
  • Seker, S.E., Mert, C., Al-Naami, K., Ozalp, N. ve Ayan, U. (2014). Time Series Analysis on Stock Market for Text Mining Correlation of Economy News. International Journal of Social Sciences and Humanity Studies, 6(1), 69-91.
  • Soysal, M. ve Ömürgönülúen, M. Ö. (2009). Türk Turizm Sektöründe Talep Tahmini Üzerine Bir Uygulama. Anatolia: Turizm AraútÕrmalarÕ Dergisi, 21 (1), 128 – 136.
  • Taú, O. ve Gürsoy, Ö.Z. (2016). A Fuzzy Logic Based Technical Indicator for BIST 30 Index and Islamic Index. Procedia Economics and Finance, 38, 203-212.
  • Tirkeú G., Güray, C. ve Çelebi, N. (2017). Demand Forecasting: A Comparison Between The Holt- Winters, Trend Analysis And Decomposition Models. Technical Gazette, 24, 503 – 509.
  • Ulusoy, T. (2010). øMKB Endeks Öngörüsü øçin øleri Beslemeli A÷ Mimarisine Sahip Yapay Sinir A÷Õ Modellemesi. UluslararasÕ øktisadi ve ødari øncelemeler Dergisi, 5, 21 – 40.
  • Ünsal, A. (1997). Zaman Serilerinde Regresyon ve Varyans Analizi Yöntemleri øle Mevsimsel DalgalanmalarÕn AraútÕrÕlmasÕ ve Bir Uygulama. Ekonomik YaklaúÕm, 8 (26), 119 – 130.
  • Üreten, S. (2006). Üretim øúlemler Yönetimi Stratejik Kararlar ve Karar Modelleri. 5.BaskÕ, Gazi Kitabevi, Ankara.
  • Winters, P.R. (1960). Forecasting Sales By Exponentially Weighted Moving Averages. Managment Science, 6 (3), 324 – 342.
  • YÕldÕz, A. ve YÕldÕz, D. (2014). BøST-100 Endeksinin ARIMA ve Yapay Sinir A÷larÕna DayalÕ Karma Yöntem øle Tahmini. Finans Politik & Ekonomik Yorumlar, 51 (588), 59 – 72.