Journal
SOFT COMPUTING
Volume 20, Issue 10, Pages 4173-4191Publisher
SPRINGER
DOI: 10.1007/s00500-015-1752-z
Keywords
Time series prediction; Stock market price prediction; Recurrent ANFIS; RENFSM; Momentum
Ask authors/readers for more resources
Neuro-fuzzy system is now one of the most widely used tools in the field of artificial intelligence systems. This study proposes a novel approach for time series stock market price prediction using a recurrent error-based neuro-fuzzy system with momentum (RENFSM). The basic idea of this approach is to use time series price momentum and time series prediction error adjusted to the well-known adaptive neuro-fuzzy inference system, ANFIS. Extended from ANFIS, the aim of this study is to propose a reliable prediction system with minimal error. Moreover, to evaluate the proposed model strength, four top-listed stocks from Dhaka stock exchange were applied. In the experiments, several choices of momentum from 3 to 20 days are selected for data preprocessing. It was found that the proposed RENFSM performed superiorly and was more reliable compared to the existing methods such as ANFIS and neural networks.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available