Stock price prediction using artificial neural network integrated moving average

research
  • 26 Nov
  • 2020

Stock price prediction using artificial neural network integrated moving average

tock prices are always interesting to be a research topic because stock prices always change at any time. Stock price index is a benchmark for shareholders to sell, buy or maintain it. As in this study, the data used is the closing price of ANTM’s share price which is then processed to predict future stock prices. The proposed method in this study is an integrated moving average which is used to transform data in order to improve data quality. So that it can improve the accuracy of predictions on the neural network. Based on the experiment conducted using 10 combinations of parameters on the neural network using integrated moving average, has been able to produce the RMSE value. And validation based on t-test also showed a significant difference compared to the previous model. So from the result of experiment use an integrated moving average proved to be able to improve neural network performance.

Unduhan

 

REFERENSI

Kirchga ̈ssner G and Wolters J, 2007 Introduction to Modern Time Series Analysis.
Chatfield C 2000 Time Series Forecasting. .
Babu C N and Reddy B E 2014 A moving-average filter based hybrid ARIMA – ANN model for forecasting time series data Appl. Soft Comput. J. 23 p.27–38
Laboissiere L A Fernandes R A S and Lage G G 2015 Maximum and minimum stock price forecasting of Brazilian power distribution companies based on artificial neural networks Appl. Soft Comput. J.
A, Adebiyi A K, Charles A O, Marion A and O, Sunday O 2012 Stock Price Prediction using Neural Network with Hybridized Market Indicators J. Emerg. Trends Comput. Inf. Sci. 3, 1 p 1–9
Rajput V and Bobde S 1989 Stock Market Forecasting Techniques: Literature Survey Int. J. Comput. Sci. Mob. Comput. B 5, 6 p. 500–506
Yip H Fan H and Chiang Y 2014 Automation in Construction Predicting the maintenance cost of construction equipment. 38 p. 30-38 Ouyang Y and Yin H, Jul 2014 A neural gas mixture autoregressive network for modelling and forecasting FX time series Neurocomputing. 135 p.171–179
Zhang G P 2004 Neural Networks in Business Forecasting. 6 .IGI Global
Bennett C J Stewart R a. and Lu J W, Apr. 2014Forecasting low voltage distribution network demand profiles using a pattern recognition based expert system Energy. 667 p.200–212.
He and Xu shaohua 2009 Process Neural Network.
Dash R 2018 Performance analysis of a higher order neural network with an improved shuffled frog leaping algorithm for currency exchange rate prediction Appl. Soft Comput. 67 p .215–231.
Anbazhagan S and Kumarappan N, Feb 2014 Day-ahead deregulated electricity market price forecasting using neural network input featured by DCT Energy Convers. Manag. 678 p711–719.
Beaumont A N 2014 Data transforms with exponential smoothing methods of forecasting Int. J. Forecast. 30, 4 p.918–927
Yager R R 2013 Exponential smoothing with credibility weighted observations Inf. Sci. (Ny). 252 p.96–105 


Hofmann M 2009 Data Mining and Knowledge Discovery Series. 6 .

Yu F and Xu X, 2014 A short-term load forecasting model of natural gas based on optimized genetic algorithm and improved BP neural network Appl. Energy. 134 p.102–113
Han J Kamber M and Pei J 2012 Data Mining: Concepts and Techniques. [19] Gorunescu 2011 Data Mining Concept Model Technique.Larose D T 2006 Data Mining Methods and Models. 

Cari

Bidang Ilmu

Kategori

Kiriman Terbaru