IJSTR

International Journal of Scientific & Technology Research

Home About Us Scope Editorial Board Blog/Latest News Contact Us
0.2
2019CiteScore
 
10th percentile
Powered by  Scopus
Scopus coverage:
Nov 2018 to May 2020

CALL FOR PAPERS
AUTHORS
DOWNLOADS
CONTACT

IJSTR >> Volume 8 - Issue 8, August 2019 Edition



International Journal of Scientific & Technology Research  
International Journal of Scientific & Technology Research

Website: http://www.ijstr.org

ISSN 2277-8616



Performance Analysis On Metaheuristic Based Hybrid Neural Network To Predict The Stock Movement

[Full Text]

 

AUTHOR(S)

K Venkatanarayana, B. Satyanarayana

 

KEYWORDS

Stock market, machine learning, artificial neural network, HMNN, metaheuristics,Optimization

 

ABSTRACT

Stock market prediction is a time series forecasting problem. For an efficient stock price prediction, in this paper optimization based neural network learning scheme has been developed that alleviates the existing Artificial Neural Network (ANN) limitations such as local minima and convergence issues. The existing gradient descent based algorithms are local search algorithms. To find global optimum solution, Metaheuristic based Hybrid Neural Network (HMNN) has been developed. The hybrid neural network executes optimization of activation nodes, optimization of weights and learning parameters. To illustrate this, we apply the proposed HMNN method to study the movement of closing prices of stock market. The algorithm has been practically examined for performance in terms of Mean Absolute Percentage Error, accuracy, precision, recall, completeness, F-measure where it has performed better as compared to major existing schemes. The proposed scheme exhibited 94.97% prediction accuracy while guarantee optimal precision, F-measure and recall.

 

REFERENCES

[1] Min B. Shrestha et al,” Selecting appropriate methodological framework for time series data Analysis”, The Journal of Finance and Data Science 4 (2018) p 71-89
[2] Saahil Madge “ Predicting Stock Price Direction using Support Vector Machines” Independent Work Report Spring 2015.
[3] G. S Atsalakis et al , "Surveying stock market forecasting techniques - Part D: Soft computing methods," Expert Systems with Applications, vol. 36, no. 3, pp. 5932-5941, April 2009.
[4] S.N.H.S.Hussin et al” Hybrid Metaheuristic of Artificial Neural Network - Bat Algorithm in Forecasting Electricity Production and Water Consumption at Sultan Azlan Shah Hydropower Plant” 978-1-5090-2547-3/16 ©2016 IEEE.
[5] Feng Zhou ,hao-min et “EMD2FNN: A strategy combining empirical mode decomposition and factorization machine based neural network for stock market trend prediction” Volume 115, January 2019, Pages 136-151]
[6] Muh Faisal Dinniy et al “Quality Measurement Classification for Water Treatment using Neural Network with Reinforcement Programming for Weighting Optimization” 2016 Knowledge Creation and Intelligent Computing (KCIC).
[7] Susana de León-Aldaco et al ” Metaheuristic Optimization Methods Applied to Power Converters: A Review” 10.1109/TPEL.2015.2397311, IEEE Transactions on Power Electronics.
[8] Jolliffe. Principal component analysis. Springer series in statistics. Springer, New York u.a., 1986.
[9] HUANG Jie et al “ An Improved kNN Based on Class Contribution and Feature Weighting” 2018 10th International Conference on Measuring Technology and Mechatronics Automation
[10] X.S.Yang et al, Firefly algorithms for multimodal optimization, in: Stochastic Algorithms:Foundations and Applications, SAGA 2009, Lecture Notes in Computer Sciences,Vol.5792, 2009, pp. 169-178
[11] Bexultan Nursultan , “Perceptron Linear Activation Function Design with CMOS-Memristive Circuits” IEEE 978-1-5386-5928-1/18/ 2018
[12] www. finance. yahoo.com