Efficient forecasting of financial time-series data with virtual adaptive neuro-fuzzy inference system Online publication date: Thu, 03-Nov-2016
by Sarat Chandra Nayak; Bijan Bihari Misra; Himansu Sekhar Behera
International Journal of Business Forecasting and Marketing Intelligence (IJBFMI), Vol. 2, No. 4, 2016
Abstract: Uncertainties and non-linearity associated with the stock index make it difficult to predict its behaviour and hence it remains a challenging task for researchers. Newly developed intelligent machine learning techniques have been applied to this area and these have established as efficient forecasting models. This paper presents a Virtual Adaptive Neuro-Fuzzy Inference System (VANFIS) for efficient forecasting of stock market indices. VANFIS works in a virtual environment where the Adaptive Neuro-Fuzzy Inference System (ANFIS) is exposed to virtual data positions to infer the future stock price. This model does not take any actual data at any point of time as its input, but works completely in the virtual environment. To validate the performance of the proposed model, 15 years' data from ten stock markets are taken and five different performance metrics are evaluated. Simulation results show that VANFIS significantly improves forecasting performance in comparison to ANFIS.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Business Forecasting and Marketing Intelligence (IJBFMI):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com