Predicting stock output of Banks listed in Tehran Stock Exchange using financial ratios with neural network approach
Abstract
 Timely prediction of stock output can help managers and investors to make better decisions. Nowadays, the use of innovative approaches to artificial intelligence in modeling and financial forecasting has become commonplace.
Banking industry, with 17 companies in Tehran Stock Exchange and OTC, is one of the groups paid attention by investors and especially risk averse people who except appropriate profit sharing and moderate rising slope of stock. This study aimed to investigate the prediction of stock output of Banks listed in the Tehran Stock Exchange using 7 financial ratios in the span of 2009 to 2015 with two approaches of Artificial Neural Networks (ANNS) and Support Victor Regression (SVR) as two techniques of artificial intelligence and data analysis and are used for prediction. Then, two methods were compared using the criteria for the function evaluation. The results of the study show that Support Victor Regression has better capability than the Artificial Neural Networks to predict stock output of Banks listed in Tehran Stock Exchange.
Full Text:
PDFReferences
Raee, R. (1998). Appropriate investments design in portfolio using artificial intelligence (neural networks). PhD thesis on Financial Management, Tehran University.
Azar, A., Rajab Zadeh, A. (2003). Assessing combination anticipation: by neural-classic network approach in the field of Economics, Journal of Economic Research, No. 63, 87-114. Persian
Xiong, T., Yukun, B., Zhongyi, H. (2013). Multiple output support vector regression with a firefly algorithm for interval valued stock price index forecasting, Elsevier B.V.
Raee, R., Chavoshi, K. (2003). Predicting the stock output in Tehran Stock Exchange: Artificial Neural Networks Model and Multi-Factor Model. Journal of Financial Research, Management Faculty of Tehran University. 5 (15), 97-120.
Örkcü, H., Bal, H. (2011). Goal programming approaches for dataenvelopment analysis cross efficiency evaluation. Applied Mathematics and Computation. 218 (2), 346-356.
Basheer, I. A., Hajmeer, M. (2000). Artificial neural networks: fundamentals, computing, design and application. Journal of Microbiological Methods. (43), 3-31.
Omran, M., Ragab, A. (2004). Linear versus non-linear Relationshipsbetween Financial Ratios and stock Return. Review of Accounting & finance. 3(2), 84-103.
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
World of Researches Publication