زمانسنجی بازار با در نظرگیری شاخص احساسات سرمایه‌گذار در بورس اوراق بهادار تهران

نوع مقاله : مقاله پژوهشی

نویسندگان

1 کارشناسی ارشد مهندسی مالی، دانشگاه صنعتی خواجه نصیرالدین طوسی، تهران، ایران.

2 دانشیار، گروه مهندسی صنایع، دانشگاه صنعتی خواجه نصرالدین طوسی، تهران، ایران.

3 استادیار، گروه مهندسی صنایع، دانشگاه صنعتی خواجه نصرالدین طوسی، تهران، ایران.

چکیده

زمان‌سنجی بازار اتخاذ تصمیمات سرمایه‌گذاری با یک استراتژی معاملاتی مکانیکی براساس برخی معیارهای اقتصاد کلان است. در این تحقیق، شاخص احساسات سرمایه‌گذار و شاخص‌های اقتصاد کلان نظیر تورم، نرخ ارز، رشد اشتغال و تولید ناخالص حقیقی متغیرهای نماینده برای زمان‌سنجی بازار به منظور پیش‌بینی جهت و بازده شاخص کل بورس اوراق بهادار تهران مورد استفاده قرار گرفت. در این راستا از چهار مدل رگرسیون لجستیک، لسو، ستیغی و الستیک‌نت با استفاده از داده‌های ماهانه در دوره زمانی 1395 تا 1399 استفاده شد. به منظور توسعه شاخص احساسات، با بهره‌گیری از مدل تحلیل عاملی اکتشافی، از شش متغیر احساسی مختلف استفاده شد که در نهایت، سه متغیر نسبت سهام در سبد صندوق‌های سرمایه‌گذاری، شاخص قیمت و شاخص ۵۰ شرکت برتر برگزیده شدند. خروجی مدل رگرسیون لجستیک به منظور پیش‌بینی براساس تک شاخص با مقدار پیش‌بینی براساس دیگر شاخص‌ها مقایسه گردید که نتیجه حاکی از برتری پیش‌بینی لجستیک براساس همه متغیرها نسبت به پیش‌بینی لجستیک براساس تک شاخص داشت. مقایسه سه مدل لاسو، ستیغی و الستیک‌نت، برای پیش‌بینی نشان داد که قدرت و دقت مدل رگرسیون ستیغی بیشتر از دو مدل دیگر بود به علاوه دو مدل لسو و الستیک‌نت تقریبا دقت برابری داشتند. نتایج این تحقیق می‌تواند برای شرکت‌های سرمایه‌گذاری و سبدگردان، تحلیل‌گران و سرمایه‌گذاران مفید باشد.

کلیدواژه‌ها


عنوان مقاله [English]

Market Timing by Considering the Investor Sentiment Index in Tehran Stock Exchange

نویسندگان [English]

  • Fatemeh Tahernezhad 1
  • Amir Abbas Najafi 2
  • Hossein Mohseni 3
1 Msc in Financial Engineering, K.N. Toosi University of Technology, Tehran, Iran.
2 Associate prof., Department of Industrial Engineering, K.N. Toosi University of Technology, Tehran, Iran.
3 Assistant Prof., Department of Industrial Engineering, K.N. Toosi University of Technology, Tehran, Iran.
چکیده [English]

Market timing Investment decisions are made with a mechanical trading strategy based on certain macroeconomic criteria. In this study, investor sentiment index and macroeconomic indicators such as inflation, exchange rate, employment growth and real GDP of representative variables were used to market timing to predict the direction and return of the total index of Tehran Stock Exchange. In this regard, four models of logistic regression, Lasso, Ridge and Elastic Net were used using monthly data in the period 1395 to 1399. In order to develop the sentiment index, using the exploratory factor analysis model, six different emotional variables were used, and finally, three variables of stock ratio in the portfolio of investment funds, Tehran price index and top 50 index were selected. The output of the logistic regression model for forecasting based on a single index was compared with the value of forecasting based on other indicators, which showed that logistics forecasting based on all variables was superior to logistic forecasting based on a single index. Comparison of Lasso, Ridge and Elasticnet models for prediction showed that the strength and accuracy of Ridge regression model was more than the other two models, in addition, Lasso and Elasticnet models were almost equally accurate. The results of this research can be useful for investment companies and portfolio managers, analysts and investors.

کلیدواژه‌ها [English]

  • Market Timing
  • Exploratory Factor Analysis
  • Logistic Regression
  • Ridge Regression
  1. Altinbas, Hazar and Biskin, Osman Tayfun. (2015). Selecting Macroeconomic Influencers on Stock Markets by Using Feature Selection Algorithms. Procedia Economics and Finance, 30, pp. 22-29.
  2. Azarbooye, N. (2020). An overview of investor’s emotional behavior and its effects on the stock market. Geography and human relation, 3(2), 16-26. (in Persian)
  3. Aziz Khan, M., & Ahmad, E. (2018). Measurement of Investor Sentiment and Its Bi-Directional Contemporaneous and Lead–Lag Relationship with Returns: Evidence from Pakistan. Sustainability, 11(1), 1-20.
  4. Badri, A. (2009). Behavioral financial knowledge and asset management. Tehran, Kayhan. (in Persian)
  5. Banchit, A., Abidin, S., Lim, s., & Morni, F. (2020). Investor Sentiment, Portfolio Returns, and Macroeconomic Variables. Journal of Risk and Financial Management, 13(11), 259-273.
  6. Bashir pour, A., Saber, E., & Mohseni, H. (2016). Market Timing. Tehran: Bourse Publications affiliated with Bourse Information and Services Company. (in Persian)
  7. Borucka, A., & Grzelak, M. (2019). Application of logistic regression for production machinery efficiency evaluation. Applied Sciences, 9(22), 4770.
  8. Chen, H., Chong, T. T. L., & She, Y. (2013). A Principal Component Approach to Measuring Investor Sentiment in China. Quantitative Finance, 14(4), 573-579.
  9. De Long, D., Shleifer, A., Summers, H., & Waldman, J. (1990). Noise Trader Risk in Financial Markets, Journal of Political Economy, 98, 703╶ 738.
  10. Dehghani, M. Mohammad, M & Ansari-samani, H. (2019). Machine learning algorithms for time series in financial markets. Journal of Soft Computing and Information Technology,8(3), 1-67.
  11. Ebrahimi Sarve Olia, M.H., Babajani, J., Hanafizadeh, P. & Ebadpour, B. (2017). Assessment of the Behavioral Determinants of Individual Investors in Tehran Stock Exchange Based on Structural Equation Modeling. Journal of Investment Knowledge, 6(22), 131-146. (In Persian)
  12. Fama, E. (1970), Efficient Capital Markets: AReview of Theory and Empirical Work, Journal of Finance, 25, 383-417.
  13. Farahani, H. (2020), Comparing Linear Regression to Shrinkage Regression Algorithms (RR, Lasso, El Net) Using PTSD Patients’ Data. Journal of Applied Psychological Research, 11(3), 193-206.
  14. Farhadi, R., Akhoundi, O., & Mehr Avar, H. R. (2019). Explaining the Relationship between Herding Behavior and Momentum with Stock Returns: Evidence from the Iran Capital Market. Journal of Financial Management Perspective, 26, 121-145. (In Persian)
  15. Fayyazi, H., & Goshtasbi Maharlouei, R. (2015). Relationship between Investors Sentiment Index with First and Second Market Indexes in Tehran Stock Exchange (TSE). Ciência e Natura, 37(4), 16-24. (in Persian)
  16. Ghatak, A. (2017). Machine Learning with R. translate: Abbas nezhadvarzi, R., Elikaee Ahari, M., & Vahidi, Javad. (2020). Babol: Fanavari Novin.
  17. Hashmi, H., Dadashi, I., Gholamnia, Hamid Reza. & Yahyazadefard, M. (2021). Application of Machine Learning Methods (GPR-LASSO) To predict the Value of Firms Listed in Tehran Stock Exchange, Journal of Empirical Research in Accounting, 11(2), 71-98. (in Persian)
  18. Heidarpoor, F., Tariverdi, Y., & Mehrabi, M. (2014). The Impact of Investor Sentiment on the Stock Returns. Quarterly Financial Knowledge of Security Analysis, 6 (1), 1-13. (In Persian)
  19. Hemmatpour, S. & Hashemi, H. (2011). Using PCA and RDA feature reduction techniques for ranking seismic attributes. Journal of Earth and Space Physics, 37(4), 217-227. (in Persian)
  20. Hu, J., Sui, Y., & Ma, F. (2021). The Measurement Method of Investor Sentiment and Its Relationship with Stock Market. Computational Intelligence and Neuroscience, 1-11.
  21. Kaiser, H. F., & Cerny, B. A. (1977). A Study of a measure of sampling adequacy for factor analytic correlation matrices. Multivariate Behavior Research, 12(5), 43-47.
  22. Kamravafar, M. & Zabihollah Hashemi, s. (2017). Analysis of Most Important Variables Affecting TEPIX and Modeling Them with Artificial Neural Networks and Comparing Results with Technical Analysis and Elliott Waves. Financial Engineering & Securities Management, 8(30), 169-184. (In Persian)
  23. Kim, T., & Ha. A. (2010). Investor Sentiment and Market Anomalies. 23rd Australasian Finance and Banking Conference 2010 Paper.
  24. 24. Larisemnani, B., & Dehkhoda, A. (2020). Investigating the Impact of Mood on the Behavioral Finance Trap of Investors in Tehran Stock Exchange. Journal of Financial Management Perspective, 30, 143-162. (in Persian)
  25. Lee, P. (2019). The Empirical Study of Investor Sentiment on Stock Return Prediction. International Journal of Economics and Financial Issues, 9(2), 119-124.

26 Link, Lucio and Frota Decourt, Roberto. (2016). Stock returns, macroeconomic variables and expectations: Evidence from Brazil. Revista científica Pensamiento y Gestión, (40), pp. 91–112.

  1. Maronna, R. A. (2011). Robust ridge regression for high-dimensional data. Technometrics. 53(1), 44-53.
  2. Mascio, David A. (2018). Forecasting Market Direction with Sentiment Indices.Ph.D.thesis. Edhec Business School.
  3. Mascio, David A. Fabozzi, Frank J. & Zumwalt, J. Kenton. (2021). Market timing using combined forecasts and machine learning. Journal of Forecasting. 40(1), pp. 1-16.
  4. Mazviona, B. W. (2015). Measuring Investor Sentiment on The Zimbabwe Stock Exchange. Asian Journal of Economic Modelling, 3(2), 21-32.
  5. Mitchell, T. M. (1997). Machine Learning. McGraw Hill.
  6. Mohaddeth, F. (2010). Principal component analysis and surveying factors. Case study: Extracting assets price index and studying its effect on inflation. Central Bank of Iran, https://cbi.ir/datedlist/4274.aspx. (In Persian)
  7. 33. Osoolian, M., & Safari, M. (2015). Investors trading activity: A behavioral perspective and empirical results. Journal of Financial Management Perspective, 5(11), 27-52. (In Persian).
  8. Park, H., & Konishi, S. (2015). Robust logistic regression modelling via the elastic net-type regularization and tuning parameter selection. Journal of Statistical Computation and Simulation. 86(7), 1-12
  9. Pashootanizadeh, H., Ranaei Kordshouli, H., Abbasi, A., & Moosavihaghighi, M. (2020). Simulation the Model of Effects of Behavioral and Macroeconomic Factors on the Tehran Stock Exchange Index with Using System Dynamics Approach. Journal of Financial Management Perspective, 29, 89- 124. (in Persian)
  10. Pirasteh, A., & Hidarnia, A. (2008). Exploratory Factor Analysis of Psychosocial determinats measures of physical activity amony Iranian adolescent Girls. Journal of Medical Council of Islamic Republic of Iran, 26(4), 474-485. (in Persian)
  11. Peng, Yaohao. Albuquerque, Pedro Henrique Melo. Kimura, Herbert & Saavedra, Cayan Atreio Portela Bárcena. (2021). Feature selection and deep neural networks for stock price direction forecasting using technical analysis indicators. Machine Learning with Applications, 5.
  12. 38. Rodposhti, F. R., Heybati, F., & Mousavi, S. R. (2012). Mathematical Model of Behavioral Approach to Portfolio Selection. Financial Engineering and Portfolio Management, 3(12), 17-37. (In Persian)
  13. Shah, Dev. Isah, Haruna & Zulkernine, Farhana. (2019). Stock Market Analysis: A Review and Taxonomy of Prediction Techniques. International Journal of Financial Studies, 7(2), pp. 26-48.
  14. Sheikholeslami, A., Baqeri Khalili, F., & Mahmoodabadi, A. (2012). Application of principal component analysis as a variables reduction technique in freeway accident prediction models; A case study. Journal of Transportation Engineering, 3(4), 325-338. (In Persian)
  15. Sinaei, H. Mortazavi, S. & Teimuri asl, Y. (2005). Predicting the Tehran Stock Exchange index using artificial neural networks. Accounting and Auditing Review, 12(3), 59-83. (In Persian)
  16. 42. Taghavi, R., Dadashi, I., zare bahnamiri, M., & Gholamnia roshan, H. (2020). Predicting Emotional Tendency of Investors Using Support Vector Machine (SVM) and Decision Tree (DT) Techniques. Financial Engineering and Portfolio Management, 11(45), 544-570. (In Persian)
  17. Tohidi, Mohammad. (2020). Extracting Composite sentiment Index for Tehran Stock Exchange. Asset Management and Financing, 8(2), 49-68. (in Persian)
  18. Ui Hadia, N., Abdullah, N., & Sentosa, L. (2016). An Easy Approach to Exploratory Factor Analysis: Marketing Perspective. Journal of Educational and Social Research, 6(1).
  19. Yang, Bing, Zi-Jia Gong, and Wenqi Yang. (2017). Stock Market Index Prediction Using Deep Neural Network Ensemble. Paper Presented at the 2017 36th Chinese Control Conference (CCC), Dalian, China, July 26–28.
  20. 46. Yung-Chou, L. (2005). The trading volume trend, investor sentiment, and stock returns. PhD. Louisiana State University.
  21. Zhang, Q., & Yang, S. (2009). Noise Trading, Investor Sentiment Volatility, and Stock Returns. Systems Engineering — Theory & Practice, 29(3), 40–47.
  22. Zhong, Xiao & Enke, David. (2019). Predicting the daily return direction of the stock market using hybrid machine learning algorithms. Financial Innovation, 5(4).