کاربرد مدل ساز اقتصاد سنجی جهت پیشبینی قیمت سهام در بازار سرمایه
محورهای موضوعی : مهندسی مالی
علیرضا سادات نجفی
1
(گروه مدیریت فناوری اطلاعات، واحد تهران شمال، دانشگاه آزاد اسلامی، تهران، ایران.)
سهیلا سردار
2
(گروه مدیریت صنعتی، واحد تهران شمال، دانشگاه آزاد اسلامی، تهران، ایران .)
کلید واژه: بازار سرمایه, پیشبینی, مدل ساز اقتصاد سنجی, تحلیل داده‌ها,
چکیده مقاله :
یکی از روشهای مطرح در بررسی علمی بازار سرمایه استفاده از مدل سازهای اقتصاد سنجی می باشد . در پژوهشهای انجام شده اغلب مدلسازهای اقتصاد سنجی محدود، بدون مقایسه و بررسی میزان خطای پیشبینی سایر الگوریتم‌ها ، مورد بررسی قرار گرفته اند . در این پژوهش برای رفع این نقیصه با اجرا و مقایسه روش های مطرح برروی سهم های منتخب و بر اساس پارامترهای ارائه شده کارا ترین الگوریتم مشخص گردیده است. از سوی دیگر اغلب مرتبه جمله خود رگرسیو و مرتبه جمله میانگین متحرک جهت بررسی ها به صورت محدود در نظر گرفته می شود که بر اساس معیار اطلاعات بیزی روش تعیین درجات p و q جهت دستیابی به پاسخ بهینه را ارائه نموده ایم و با مقایسه روش های میانگین متحرک خود رگرسیو ، میانگین متحرک تجمیعی خود رگرسیو ، میانگین متحرک تجمیعی خود رگرسیو فصلی ، میانگین متحرک تجمیعی خود رگرسیو با متغیر توضیحی ،میانگین متحرک تجمیعی خود رگرسیو فصلی با متغیر توضیحی ، مدل خود رگرسیو با واریانس ناهمسانی شرطی تعمیم یافته ، مدل خود رگرسیو نمایی با واریانس ناهمسانی شرطی تعمیم یافته و مدل رگرسیون با خطاهای میانگین متحرک خود رگرسیو در بازار بورس اوراق بهادار تهران مورد بررسی قرار گرفته اند.
Investing in the capital market requires deciding on issues such as selection, timing, price and share buybacks with market research. One of the ways to do this is to use econometric modelers. In the studies performed to compare methods or to present hybrid models, most econometric models have been studied without comparing and predicting the error of prediction error of other algorithms. In this research, the most efficient algorithm for solving this defect is implemented and compared with the proposed methods on selected shares and based on the proposed parameters.On the other hand, often the order of the regression and the mean of the moving average sentence are considered for the finite number of studies, which is based on Bayesian criteria for determining the p and q degrees to obtain the optimal response. This paper compares the methods of self-regressive moving average, cumulative self-regressive moving average, self-regulated seasonal moving average, self-regressive moving average with explanatory variable, cumulative mean self-regression with explanatory variable, self-regression model with variance. Generalized conditional, exponential self-regression model with generalized conditional heterogeneity variance and regression model with moving average self-regression errors for selected symbols of Tehran Stock Exchange.
_||_
1) Truthful Nemat, Panahian Hossein. Designing and explaining the systematic risk estimation model in a highly innovative way in Tehran Stock Exchange; Comparative approach of econometric model and artificial intelligence. Journal of financial engineering and securities management, number 35. Summer 2017.
2) Rai Reza, Amir Hashemi Seyyed Mohammad. Asset allocation is based on the prediction of econometric methods (ARMA and GARCH) and the assumption of yield uncertainty and covariance. Financial Research, Volume 18, Number 3, Pages 415-436. 2015.
3) Rai Reza, Nikahed Ali, Habibi Mostafa. Prediction of Tehran stock exchange index by combining methods of principal components analysis, support vector regression and cumulative movement of particles. Financial Management Strategy Scientific Quarterly, Al-Zahra University (S), Article 1, Volume 4, Number 4. Winter 2015.
4) Fereydon et al.'s Rudpashti guide. Investigating the effectiveness of portfolio optimization based on the stable model with classical optimization in predicting portfolio risk and return. Quarterly journal of financial engineering and securities management, number twenty-two. Spring 2014.
5) Guide to Rudpashti Fereydon, Pedram Parham. Identifying periodic and non-periodic periods of the stock market index with the modified R/S method based on fractal analysis, Journal of Financial Studies, No. 8. Winter 2019.
6) Roudpashti Fereydoun, Jalili Mohammad, Hosseinzadeh Lotfi Farhad. The conceptual framework of the application of mathematics in quantitative management studies (case study: mathematical and computer modeling in financial knowledge). Quantitative studies in management, number 2. Autumn 2019.
7) Toloi Ashlaghi Abbas, the right friend of Shadi. Stock price forecasting modeling using neural network and its comparison with mathematical forecasting methods, Economic Research Journal, Article 9, Volume 7, Number 25, Pages 237-251. Summer 2016.
8) Gholamian Elham, Davodi Seyyed Mohammad Reza. Forecasting the price trend in the stock market using random forest algorithm. Financial Engineering and Securities Management Quarterly, Islamic Azad University, Central Tehran Branch, Article 14, Volume 9, Number 35, Pages 301-322. Summer 2017.
9) Asl Hasan carpet maker, Masoom Zadeh Nasim. Predicting the probability of stock price changes using logistic regression in Tehran Stock Exchange. Accounting and auditing research. Iran Accounting Association, second year, number 5. Spring 2019.
10) Qolizadeh Mohammad Hassan, Vahidpour Qasim. Stock price prediction with fuzzy regression method. Macroeconomics scientific research journal, Mazandaran University, 6th year, number 12. 1390.
11) Makian Seyyed Nizamuddin. Mousavi Fatima Al-Sadat. Pars Oil Products Company stock price prediction using neural network and regression method: case study: Pars Oil Products Company stock price. Economic Modeling Quarterly, 6th year, number 2, page 105-121. Summer 1991.
12) Homayoun Asdaleh and colleagues. Evaluation of forecasting models of Iranian stock market indicators. Economic Research and Policy Quarterly, 18th year, number 56, pages 95-112. Winter 389.
13) AISHWARYA SINGH. A Practical Introduction to K-Nearest Neighbors Algorithm for Regression. https://www.analyticsvidhya.com
14) Alexander, Carol. Quantitative Methods in Finance, John Wiley & Sons Ltd, The Atrium, Southern Gate, Chichester. (2008)
15) Dev Shah Haruna Isah, Zulkernine Farhana. Stock Market Analysis: A Review and Taxonomy of Prediction Techniques. International Journal of Financial Studies, 7(26). (2019)
16) Hiransha, M., E. A. Gopalakrishnan, Vijay Krishna Menon, and Soman Kp. NSE stock market prediction using deep-learning models. Proceedings of Computer Science 132: 1351–62. (2018)
17) Olson, D. & C. Mossman. Neural Network of Canadian Stock Returns Using Accounting Ratios. International Journal of Forecasting, Vol. 19, pp. 453-465. (2003)
18) Teall John, Hasan Iftekhar. QUANTITATIVE METHODS FOR FINANCE AND INVESTMENTS, Blackwell Publishers. (2002)
19) Yuling LIN Haixiang GUO, Jinglu HU. An SVM-based approach for stock market trend prediction. Proceedings of International Joint Conference on Neural Networks, Dallas, Texas, USA. (2013)