ABSTRACT:

Reliable forecasting techniques for financial applications are important for investors either to make profit by trading or hedge against potential market risks. In this paper the efficiency of a trading strategy based on the utilization of a neurofuzzy model is investigated, in order to predict the direction of the market in case of FTSE100 and New York stock exchange returns. Moreover, it is demonstrated that the incorporation of the estimates of the conditional volatility changes, according to the theory of Bekaert and Wu (2000), strongly enhances the predictability of the neurofuzzy model, as it provides valid information for a potential turning point on the next trading day. The total return of the proposed volatility-based neurofuzzy model including transaction costs is consistently superior to that of a Markov-switching model, a feedforward neural network as well as of a buy & hold strategy. The findings can be justified by invoking either the “volatility feedback” theory or the existence of portfolio insurance schemes in the equity markets and are also consistent with the view that volatility dependence produces sign dependence. Thus, a trading strategy based on the proposed neurofuzzy model might allow investors to earn higher returns than the passive portfolio management strategy.


Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here


PROJECT TITLE :DPPred: An Effective Prediction Framework with Concise Discriminative Patterns Sign In or Purchase - 2018ABSTRACT:In the literature, two series of models are proposed to deal with prediction issues together with
PROJECT TITLE : Provably Secure Dynamic Id-Based Anonymous Two-Factor Authenticated Key Exchange Protocol With Extended Security Model Sign In Or Purchase - 2017 ABSTRACT: Authenticated key exchange (AKE) protocol permits a
PROJECT TITLE : Traffic Sign Detection and Recognition - 2015 ABSTRACT: This paper proposes a unique system for the automatic detection and recognition of traffic signs. The proposed system detects candidate regions as maximally
PROJECT TITLE: Fast Sign Detection Algorithm for the RNS Moduli Set {2n+1 − 1, 2n − 1, 2n} - 2014 ABSTRACT: Sign arithmetic is ineluctable in digital signal processing algorithms. Due to the way signed integer is represented
PROJECT TITLE :Spelled sign word recognition using key frameABSTRACT:During this study, the authors gift a new system for sign language hand gesture recognition. Using video input, the system can recognise any spelled word or

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry