بررسی خطای پیش‌بینی تغییرات شاخص قیمت سهام در صنعت مواد و محصولات دارویی با استفاده از الگوریتم‌های هوش مصنوعی

نوع مقاله: مقاله پژوهشی

نویسندگان

1 استادیار حسابداری دانشگاه پیام نور

2 استادیار حسابداری دانشگاه فردوسی مشهد

3 کارشناس ارشد حسابداری از دانشگاه آزاد اسلامی واحد علوم و تحقیقات خراسان جنوبی

چکیده

مقدمه: شاخص قیمت سهام بورس نشان‌دهنده وضعیت اقتصادی کلی یک کشور است. به همین دلیل، پیش‌بینی این شاخص برای سرمایه‌گذاران از اهمیت بسزایی برخوردار است. هدف پژوهش حاضر پیش‌بینی تغییرات شاخص قیمت سهام در بورس اوراق بهادار تهران با استفاده از شبکه‌های عصبی است.
روش پژوهش: برای انجام این پژوهش از داده‌های شرکت‌های صنعت مواد و محصولات دارویی پذیرفته شده در بورس اوراق بهادار تهران در بازه زمانی 1391-1385 استفاده شده است. از بین 48 متغیر ورودی 10 متغیر به وسیله الگوریتم بهینه‌سازی حرکت دسته‌جمعی ذرات انتخاب شد. این الگوریتم ترکیب بهینه‌ای از متغیرهای تأثیرگذار را شناسایی کرده که متغیرهای مستقل این پژوهش است. سپس، داده‌های مربوط به متغیرهای انتخاب شده به طور جداگانه به الگوریتم‌های کرم شب‌تاب، توابع پایه شعاعی، شبکه‌های چند لایه پرسپترون، رقابت استعماری و شبکه تطبیقی بر اساس نظام‌های با منطق فازی وارد شد و این الگوریتم‌ها آموزش داده شد. در ادامه، الگوریتم‌های مذکور با داده‌های ارزیابی، آزموده شده و به این ترتیب خطای پیش‌بینی مشخص و بر اساس آن به مقایسه روش‌ها پرداخته شد. برای این منظور از نرم‌افزارهای متلب نسخه‌های 6 و 7 و  SPSSنسخه 11 استفاده شد.
یافته‌ها: استفاده از متغیرهای تأثیرگذار بر پیش‌بینی تغییرات شاخص قیمت سهام در الگوریتم‌های مورد استفاده در پژوهش حاضر توانسته است خطای پیش‌بینی تغییرات شاخص قیمت سهام در سطح صنعت مواد و محصولات دارویی را کاهش دهد.
نتیجه‌گیری: نتایج پژوهش نشان می‌دهد که الگوریتم رقابت استعماری عملکرد بهتری نسبت به سایر الگوریتم‌ها دارد. هم‌چنین، الگوریتم‌های پیشنهادی در مجموع توانایی بالایی در پیش‌بینی شاخص قیمت سهام دارد و خروجی داده‌ها برای الگوریتم رقابت استعماری، ضریب همبستگی 9404/0 را نشان می‌دهد.

کلیدواژه‌ها


عنوان مقاله [English]

Investigating the Prediction Error of the Stock Price Index Changes in the Material Industry and Pharmaceutical Products via Artificial Intelligence Algorithms

نویسندگان [English]

  • M. Mousavi Shiri 1
  • M. Salehi 2
  • K. Hamidehpour 3
1 Assistant Professor, Department of Accounting, Payame Noor University
2 Assistant Professor, Department of Accounting, Ferdowsi University of Mashhad
3 M. A. in Accounting, Islamic Azad University, Science and Research Branch, Khorasan-e Jonoubi
چکیده [English]

Introduction: The stock price index represents the overall economic situation of a country. Therefore, predicting this index is important for investors. The aim of this research is predicting the stock price index changes of the Tehran Stock Exchange by using neural networks.
Method: In order to carry out this research, the data collected from the material industry and pharmaceutical products listed on the Tehran Stock Exchange during 2007-2013 have been used. Among 48 input variables, 10 input variables were selected by Particle Swarm Optimization Algorithm. This algorithm identifies an optimal combination of influential variables which include the independent variables of this research. Afterwards, the data relevant to the selected variables were inserted separately into the Firefly Algorithms, Radial Basis Functions, Multi-Layer Perceptron Networks, Imperialist Competitive Algorithm, and Adaptive Grid Scheme based on the Fuzzy Logic Systems, and then, these algorithms were taught. Next, the above mentioned algorithms have been tested by the estimated data; hence, the prediction error has been identified, and according to that, these methods have been compared. For this purpose, SPSS Software Version 11 and MATLAB Software Versions 6 and 7 were used.
Results: Applying the influential variables in the predicting of the stock price index changes in the used algorithms in this research can reduce the prediction errors of the stock price index in the material industry and pharmaceutical products.
Conclusion: The results of the research show that the Imperialist Competitive Algorithm has a better performance in relation to the other algorithms. Moreover, the suggested algorithms, in general, have a high ability in predicting the stock price index, and the output data for Imperialist Competitive Algorithm indicate the correlation coefficient of 0.9404.

کلیدواژه‌ها [English]

  • Fuzzy Algorithms
  • Materials Industry and Pharmaceutical Products
  • The Stock Price Index Changes
1      Salehi, M.; Kardan, B.; and Z. Aminifard (2012).“Effective Components on the Forecast of Companies’ Dividends Using Hybrid Neural Network and Binary Algorithm Model”, Indian Journal of Science and Technology, Vol. 5, No. 9,pp. 3321-3327.

2      Monjamy, A.; Abzari, M.; and A. Raayati Shavazi (2009). “Predicting the Stock Price in the Stock Market Using Fuzzy Neural Networks and Genetic Algorithms, and by Comparingit with Artificial Neural Network”,Journal of Quantitative Economics (Economics Review), Vol. 6, No.3, pp. 1-26. [In Persian]

3      Kara, Y. and O. Baykan (2011). “Predicting Direction of Stock Price Index Changes Using Artificial Neural Networks and Support Vector Machines: The Sample of the Istanbul Stock Exchange”, Expert Systems with Applications, Vol. 36, No. 2, pp. 3355-3366.

4      Dadashi, I.; Asghari, M.; Zareii, S.; and M. Jafari baii (2013). “Examining the Effect of Capital Structure and Financing on the Technical Efficiency of Pharmaceutical Companies Listed on the Tehran Stock Exchange”, Journal of Health Accounting, Vol. 2, No. 1, pp. 19-1. [In Persian]

5      Mirzaee, H.; Khataii, M.; and Y. Ghanbari (2013). “Investigating the Relationship between Business Risk and Financial Risk with Performance of Pharmaceutical Companies Listed on the Tehran Stock Exchange”, Journal of Health Accounting, Vol. 2, No. 2, pp. 77-91. [In Persian]

6      Kennedy, J. and R. Eberhart (1995).“Particle Swarm Optimization”, Proceedings of IEEE International Conference on Neural Networks, Piscataway, NJ, 27 November, pp. 1942-1948.

7      Ansari, Z. and M. Kazemi (2012).“Predicting the Accounting Earnings by Using Multi-Layer Neural Networks Perceptron (MLP) with Comparison to Artificial Neural Networks of Radial Basis Functions (RBF)”, The 1st National Conference on Investigating Methods of Improving Issues in Management, Accounting and Industrial Engineering in Organizations, Gachsaran Islamic Azad University, 2 and 3 February. [In Persian]

8      Tavakkoli Heravi, P. and A. Karimpour (2013). “Reinforced Clustering Fuzzy Neural Networks (ANFIS)”, The 21st Iranian Conference on Electrical Engineering, Shahid Beheshti University Tehran, 14 to 16 May. [In Persian]

9      Pourkazemi, M.; Fattahi, M.; Mazaheri, S.; and B. Asadi (2013). “The Optimization of Portfolio Projects with the Interaction of Colonial Competitive Algorithm (ICA)”, Journal of Industrial Management, Vol. 5, No. 1, pp. 1-20. [In Persian]

10  Yosefi, A. and H. Ebrahim Khani (2012). “The Investigation and Development of Firefly Algorithm for Solving Job Shop Scheduling Problem”, The 9th International Conference on Industrial Engineering, Khajeh Nasir Toosi University of Technology, Tehran, 1 and 2 January. [In Persian]

11  Heydari Zare, B. and H. Kordlouyi (2010). “Predicting the Stock Price by Using Artificial Neural Networks”, Scientific Journal of Management, Vol. 1, No. 17, pp. 49-57. [In Persian]

12  Pak Din Amiri, A.; Pak Din Amiri, M.; and M. Pak Din Amiri (2009). “Presenting the Model for Predicting the Total Stock Price Index with a Neural Networks Approach”, Journal of Economic Literature, Vol. 6, No. 11, pp. 83-108. [In Persian]

13  Kao, L.; Chiu, C.; Lu, C.; and C. Chang (2012).“A Hybrid Approach by Integrating Wavelet-Based Feature Extraction with MARS and SVR for Stock Index Forecasting”, Decision Support Systems, Vol. 54, No. 3 pp. 1228-1244.

14  Hsieh, L.; Hsieh, S; and P.Tai (2011). “Enhanced Stock Price Variation Prediction via DOE and BPNN-based Optimization”, Expert Systems with Applications, Vol. 38, No. 11, pp. 14178–14184.

15  Boyacioglua, M. A. and D. Avci (2010).“An Adaptive Network-Based Fuzzy Inference System (ANFIS) for the Prediction of Stock Market Return: The Case of the Istanbul Stock Exchange”, Expert Systems with Applications, Vol. 37, No. 12, pp. 7908-7912.

16  Daia, W.; Wu, J.; and Ch. Lu (2012). “Combining Nonlinear Independent Component Analysis and Neural Networks for the Prediction of Asian Stock Market Indexes”, Expert Systems with Applications, Vol. 39, No. 4, pp. 44-52.

17  Azar, A.; Afsar, A.; and P. Ahmadi (2006). “The Comparison of the Classic Methods and Artificial Intelligence for Predicting the Stock Price and Designing a Hybrid Model”, Journal of Management Research in Iran, Vol. 10, No. 4, pp. 1-16. [In Persian]

18  Behnampour, M. and A. Safari (2010). “Investigating the Relationship between the Ratio of Price to Earnings Per Share with the Earnings Quality of the Companies Listed on the Tehran Stock Exchange”, Journal of Accounting and Financial Management, Vol. 1, No. 3, pp. 128-151. [In Persian]

19  Khodayi Vale Zaghrad, M. and A. Fouladvandnia (2010). “The Evaluation of the Performance of Management of Portfolio with an Emphasis on the Downside Risk Framework of the Investment Companies Listed on the Tehran Stock Exchange”, Journal of Financial Studies, Vol. 1, No, 3, pp. 67-90. [In Persian]

20  Aghaii, M.; Kazempoor, M.; and R. Mansoor lakoroj (2013). “The Effect of Free Cash Flow and Capital Structure on Different Criteria for Evaluating the Performance of the Material Industry and Pharmaceutical Products Companies Listed on the Tehran Stock Exchange”, Journal of Health Accounting, Vol. 3, No. 2, pp. 15-1. [In Persian]