Application of Genetic Algorithm and Machine Learning Techniques for Stock Market P r e d i c t i o n

  IJCTT-book-cover
 
International Journal of Computer Trends and Technology (IJCTT)          
 
© 2016 by IJCTT Journal
Volume-36 Number-1
Year of Publication : 2016
Authors : Shibendu Mukherjee, S M Dilip Kumar
  10.14445/22312803/IJCTT-V36P110

MLA

Shibendu Mukherjee, S M Dilip Kumar "Application of Genetic Algorithm and Machine Learning Techniques for Stock Market P r e d i c t i o n". International Journal of Computer Trends and Technology (IJCTT) V36(1):59-64, June 2016. ISSN:2231-2803. www.ijcttjournal.org. Published by Seventh Sense Research Group.

Abstract -
In a financial research it is crucial to compute the expected momentum of the stocks. The objective is to reduce the risk involved in share investments and maximizing the returns of an investment. In this work, Genetic Algorithm (GA) is used to select high quality stocks with investment value from a vast pool of stocks. For the genetic algorithm to efficiently select the stocks a cogent fitness function is defined. Once defined, the elitist stock is determined. The resultant stock is clustered and a logistic regression model is built upon it. This gives a binary output for the user/customer whether to buy the stock or sell it. The experiments were conducted using RStudio and the results reveal that the proposed technique generates a higher accuracy for the prediction.

References
[1]Shipra Banik, Mohammed Anwer, et al. Dhaka stock market timing decisions by hybrid machine learning technique. In Computer and Information Technology (ICCIT), 2012 15th International Conference on, pages 384–389. IEEE, 2012.
[2]QiSen Cai, Defu Zhang, Bo Wu, and Stehpen CH Leung. A novel stock forecasting model based on fuzzy time series and genetic algorithm. Procedia Computer Science, 18:1155–1162, 2013.
[3]Ibrahim M Hamed, Ashraf S Hussein, and Mohamed F Tolba. An intelligent model for stock market prediction. International Journal of Computational Intelligence Systems, 5(4):639–652, 2012.
[4]David W Hosmer Jr and Stanley Lemeshow. Applied logistic regression. John Wiley & Sons, 2004.
[5]Phayung Meesad and Risul Islam Rasel. Predicting stock market price using support vector regression. In Informatics, Electronics & Vision (ICIEV), 2013 International Conference on, pages 1–6. IEEE, 2013.
[6]Tejas P Patalia and GR Kulkarni. Design of genetic algorithm for knapsack problem to perform stock portfolio selection using financial indicators. In Computational Intelligence and Communication Networks (CICN), 2011 International Conference on, pages 289–292. IEEE, 2011.
[7]Ruizhong Wang. Stock selection based on data clustering method. In Computational Intelligence and Security (CIS), 2011 Seventh International Conference on, pages 1542–1545. IEEE, 2011.
[8]Nimrat Kaur Sidhu, Rajneet Kaur. ”Clustering In Data Mining”International Journal of Computer Trends and Technology (IJCTT),V4(4):710-714 April Issue 2013 .ISSN 2231-2803. www.ijcttjournal.org . Published by Seventh Sense Research Group. [9]wikipedia. Confusion matrix, 2015.
[10]D.Radha Rani, A.Vini Bharati, P.Lakshmi Durga Madhuri, M.Phaneendra Babu, A.Sravani. ”Analysis of Dendrogram Tree for Identifying and Visualizing Trends in Multi - attribute Transactional Data”. International Journal of Engineering Trends and Technology(IJETT). V3(1):14-18 Jan-Feb 2012. ISSN:2231-5381. www.ijettjournal.org. published by seventh sense research group
[11]wikipedia. Logistic regression, 2015.
[12]wikipedia. Nasdaq stock market, 2015.
[13]wikipedia. R language, 2015.
[14]Chengxiong Zhou, Lean Yu, Tao Huang, Shouyang Wang, and Kin Keung Lai. Selecting valuable stock using genetic algorithm. In Simulated Evolution and Learning, pages 688–694. Springer, 2006.
[15]Min Zhu, David Philpotts, Ross Sparks, and Maxwell J. Stevenson. A hybrid approach to combining cart and logistic regression for stock ranking. The Journal of Portfolio Management, 38(1):100–109, 2011.

Keywords
Stock Market prediction, Machine Learning, Clustering, Genetic Algorithm, Logistic Regression.