The Journal of Economic Studies and Policies

The Journal of Economic Studies and Policies

A Comparative Study of Neural Networks' Capabilities Using Indicators of Technical Analysis for Forecasting of Stock's Price

Document Type : Original Article

Authors
Mahmood Motevasseli 1
Bijan Taleb Kashefi 2
1 Professor of Economics, University of Tehran
2 Master of Economics
Abstract
The most important issue for active investors in capital market is forecasting the stock's price. The main goal of this research is to study the application of stock's price anticipation by using indicators of technical analysis based on neural networks and the comparison of this method and neural networks which uses stock's price and ARIMA models. In this research stock's price of the next 10 days of 40 active companies will be anticipated in Tehran stock exchange by using three different methods. In the first method, the stock's price will be forecasted by applying SINGLE LAYER FEED FORWARD NEURAL NETWORKS. Using Levenberg-Marquardt learning algorithm and the performance criteria of   MSE with admission of market value.
In the next step, beside the entry of market value, 5, 10 and 20 days of moving average and 12 days of RSI and also ROC were introduced as new entries to the network and forecasting was accomplished. The Stock's prices were also anticipated for all companies using   ARIMA models. By   applying analysis of variance, three different anticipating models were compared. Since price anticipation for thirty companies by ARIMA models have presented better and more meaningful results rather than neural networks model. Therefore, we can claim that the linear models of ARIMA are more capable of explaining and analyzing the complexities of time series of stock's price than the nonlinear models of neural networks. Therefore, they are recommended to be used for anticipation of stock's price
Keywords
Stock's Price Forecasting
Technical Analysis
Neural Networks
Time- Series Models
Applications
منابع :
1- آذر، عادل و رجب‌زاده، علی، «ارزیابی رو‌ش‌های پیش‌بینی ترکیبی: با رویکردهای عصبی کلاسیک در حوزه اقتصاد»، مجله تحقیقات اقتصادی، 1382، شماره 61.
2- ابریشمی، حمید، اقتصاد سنجی کاربردی ،تهران، دانشگاه تهران، چاپ اول، دانشگاه تهران، 1381.
3- اصغری اسکوئی، محمد رضا، «کاربرد شبکه­های عصبی برای پیش­بینی سری­های زمانی»، فصل­نامه پژوهش­های اقتصادی، 1383.
4- پیکتن، فیلیپ، شبکه­های عصبی (اصول و کارکردها)، مهدی غضنفری و جمال ارکات، تهران، دانشگاه علم و صنعت، چاپ اول، 1383.
5- خالوزاده، حمید و خاکی، علی، «ارزیابی روش‌های پیش‌بینی قیمت سهام و ارائه مدلی غیر خطی بر اساس شبکه‌های عصبی»، مجله تحقیقات اقتصادی، 1382، شماره 63.
6- قاسمی، عبدالرسول و اسد­پور، حسن و صادقی، مختار، «کاربرد شبکه عصبی در پیش‌بینی سری‌های زمانی و مقایسه آن با مدل ARMA»، فصل­نامه پژوهشنامة بازرگانی مؤسسه مطالعات و پژوهش­های بازرگانی ،1380، شماره 18.
7- کنی، امیر عباس، مبانی تحلیل تکنیکی، تهران، چاپ اول،1383.
8- منهاج، محمد باقر، مبانی شبکه‌های عصبی، تهران، دانشگاه امیر کبیر، چاپ دوم، 1381.
9- Demult, Howard & Beale, Mark." Neural Net work toolbox for use with MATLAB." Math work Inc, 1998.
10- Essenreter, Robert. "Time series prediction with neural nets." 1996, CES.
11- Granger, C.WJ, "Forecasting stock market price: Lesson for forecasters ", working paper san Diego: university of California , department of economic,1991.
12- Martin T. Hagan & Mohammad B. Menhaj. "Training Feed forward with the Marquardt Algorithm" IEEE Transactions on Neural Network, Vol.5.no & NOV 1994.pp.989-993.
13- Plummer, Tony." The psychology of technical Analysis: profiting from crowd behavior and dynamics of price".
14- R.G.winfield, "Success in investment", John Murry prb. 1995.
15- Refines, A., A.Zapranis & G.francis:"Stock performance modeling using neural networks, A comparative study with regression models" new works, vd 7, NO .Z, 1994.
 
Send comment about this article
Enter Name.
Enter a valid email address.
Enter a vaid affiliation.
Enter comments (At leaset 10 words)
CAPTCHA Image
Enter Security Code Correctly.