Forecasting model of Shanghai and CRB commodity indexes

Golec A., Murat A., Tokat E., Turksen I. B.

EXPERT SYSTEMS WITH APPLICATIONS, cilt.39, sa.10, ss.9275-9281, 2012 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 39 Sayı: 10
  • Basım Tarihi: 2012
  • Doi Numarası: 10.1016/j.eswa.2012.02.077
  • Dergi Adı: EXPERT SYSTEMS WITH APPLICATIONS
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.9275-9281
  • Erciyes Üniversitesi Adresli: Evet

Özet

This paper examines the long-run relationship between the Shanghai index and CRB commodity index. We run our vector error correction model (VECM) for two sub-samples as pre-crisis period and post-crisis period. In pre-crisis period, there is strong bidirectional causality link between the Shanghai and CRB. In post-crisis period, there is no causality between the indices. In the second part of the article, we employ Fuzzy System Modeling (FSM) to increase the performances of root mean-square error, R-2 and Adjusted R-2. We show the results of our analysis for both Shanghai and CRB indexes. We have demonstrated the results for a good number of our investigations ANFIS, GENFIS, Classical LSE and three versions of support vector regression. For both Shanghai and CRB indexes, our FSMIFF with LSE obtains better results than all other models we have investigated and thus are more suitable for forecasting stable and unstable stock market behavior. Crown Copyright (C) 2012 Published by Elsevier Ltd. All rights reserved.

This paper examines the long-run relationship between the Shanghai index and CRB commodity index. We run our vector error correction model (VECM) for two sub-samples as pre-crisis period and post-crisis period. In pre-crisis period, there is strong bidirectional causality link between the Shanghai and CRB. In post-crisis period, there is no causality between the indices. In the second part of the article, we employ Fuzzy System Modeling (FSM) to increase the performances of root mean-square error, R-2 and Adjusted R-2. We show the results of our analysis for both Shanghai and CRB indexes. We have demonstrated the results for a good number of our investigations ANFIS, GENFIS, Classical LSE and three versions of support vector regression. For both Shanghai and CRB indexes, our FSMIFF with LSE obtains better results than all other models we have investigated and thus are more suitable for forecasting stable and unstable stock market behavior.