Stock market prediction using subtractive clustering for a neuro fuzzy hybrid approach

Title

Stock market prediction using subtractive clustering for a neuro fuzzy hybrid approach

Creator

Chandar S.K.

Description

Stock market prediction is the challenging area for the investors to yield profits in the financial markets. The investors need to understand the financial markets which are more volatile and affected by many external factors. This paper proposes a subtractive clustering based adaptive neuro fuzzy approach for predicting apple stock data prices. The research data used in this study is from 3rd Jan 2005 to 30th Jan 2015. Four technical indicators are proposed in this study. They are Simple moving average for 1week, simple moving average for 2weeks, 14days Disparity and Larry Williams R%. These variables are used as inputs to the neuro fuzzy system to predict the daily apple stock prices. Also, this study compares the proposed work with the ANFIS training method and subtractive clustering method etc. The performance of all these models is analyzed. The measures like training error, testing error, number of rules and number of parameters are calculated and compared for analysis. From the simulation results, the average performance of subtractive clustering based neuro fuzzy approach was found considerably better than the other networks. 2017, Springer Science+Business Media, LLC.

Source

Cluster Computing, Vol-22, pp. 13159-13166.

Date

2019-01-01

Publisher

Springer

Subject

ANFIS training method; Neuro fuzzy approach; Stock market prediction; Technical indicators

Coverage

Chandar S.K., Department of Management Studies, Christ University, Bengaluru, India

Rights

Restricted Access

Relation

ISSN: 13867857

Format

Online

Language

English

Type

Article

Identifier

https://doi.org/10.1007/s10586-017-1321-6

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85033572347&doi=10.1007%2fs10586-017-1321-6&partnerID=40&md5=62b0aca48d64ccd9964a4345b43a2fb0