Modeling the Total Stock Index Using the Brownian Droplet Motion Model and Comparing It with Online Machine Learning Methods

Document Type : Original Article

Authors
Rouzbeh Zarezadeh 1
Artin Beytari 2
Mohammadreza Ghorbanian 3
Hossein Badiei 4
1 Department of Accounting, Se.C., Islamic Azad University, Semnan, Iran.
2 Department of Accounting, ShQ.Z., Islamic Azad University, Tehran, Iran.
3 Department of Management, ShQ.Z., Islamic Azad University, Tehran, Iran.
4 Department of Accounting, ST.C., Islamic Azad University, Tehran, Iran.
10.22034/jik.2025.24244
Abstract
Various methods exist for comparing the explanatory power and validity of predictive models for stock price index volatility, including numerical solution methods versus their counterparts in behavioral finance literature. The benefits of comparing these models for analyzing index volatility using different approaches can enhance profitable trading strategies for investors. Accordingly, this study aimed to analyze and compare the explanatory power of numerical solution methods with the online machine learning approach. In this context, the new geometric droplet motion method and the solution model using the Fokker-Planck heuristic algorithm were compared to the online machine learning method. The statistical population of the study was the Tehran Stock Exchange price index, and the sample consisted of monthly index values from 2012 to the end of 2022. The results of detrending and the explanatory power reports of the models indicated that the explanatory power of the geometric droplet motion model exceeds that of the online machine learning model. This highlights the greater validity of trend analysis based on this model compared to the online machine learning model.
Keywords:
Geometric Droplet Motion Model, Online Machine Learning Model, Stock Price Index Volatility
  1. تفتیان، اکرم و میرزابابایی مزرعه آخوند، میلاد و اولیایی باجگانی، اخترالسادات،1402،مروری سیستماتیک بر رویکرد یادگیری ماشین در پیشبینی قیمت سهام در قالب یک مدل سری زمانی،دومین همایش ملی پژوهش های کاربردی نوین در حسابداری،دامغان،https://civilica.com/doc/1964451
  2. خسروی, آرش, & امیرحسینی, سیدمحمد جواد. (1402). ارائه ی یک روش پیش‌بینی قیمت سهام بورس به‌وسیله‌ی الگوریتم‌های بهبودیافته‌ی ترکیبی یادگیری ماشین. دوفصلنامه محاسبات و سامانه های توزیع شده, 6(1), 74-88.
  3. صراف نژاد, ریحانه, اوحدی, فرید‌ن, & معدنچی زاج, مهدی. (1402). الگوی ژئومتریک حرکت قطرۀ بهبودیافته در ارائۀ الگوی تلاطم بازارهای مالی. مدیریت تبلیغات و فروش, (), 367-377. doi: JABM.3.2.15564.350428
  4. ضیایی نجف آبادی,محمد رضا,قاضی فینی,سید رضا. (۱۴۰۲) .تحلیل و مقایسه الگوهای تحلیل نوسان آماری با روش عددی الگوریتم حرکت قطره برای شاخص قیمت سهام بورس اوراق بهادار تهران .مهندسی مالی و مدیریت اوراق بهادار ,54 (14) ,268-285.
  5. محمدی دهچشمه، خشایار و خدمتی، مجید،1402،پیش بینی روند قیمت سهام با استفاده از مدل های یادگیری ماشین،هفدهمین کنفرانس ملی پژوهش های کاربردی در علوم برق، کامپیوتر و مهندسی پزشکی،شیروان،https://civilica.com/doc/1899854

 

  1. Arias C. K., Michel, H., and Fernando Alonso-Marroquin. (2020). Stationary of detrended price return in stock markets, preprint submitted to Elsevier, Doi: arXiv.1910.01034v2.
  2. Azizeh M., M. I. Irawan, and E. R. M. Putri ,(2020), "Comparison of stock price prediction using geometric Brownian motion and multilayer perceptron", AIP Conference Proceedings 2242, 030016 (2020) https://doi.org/10.1063/5.0008066
  3. Bentis D. and Wen ting Lyu. 2022. Research on Geometric Brownian motion and its practice in pricing. In 2022 3rd Asia Service Sciences and Software Engineering Conference (ASSE' 22). Association for Computing Machinery, New York, NY, USA, 161–164. https://doi.org/10.1145/3523181.3523204
  4. Brătian, Ana-Maria Acu, Diana Marieta Mihaiu, Radu-Alexandru Șerban. (2022) Geometric Brownian Motion (GBM) of Stock Indexes and Financial Market Uncertainty in the Context of Non-Crisis and Financial Crisis Scenarios. Mathematics 10:3, 309
  5. Chahuán-Jiménez, K. (2024). Neural Network-Based Predictive Models for Stock Market Index Forecasting. Journal of Risk and Financial Management, 17(6), 242. https://doi.org/10.3390/jrfm17060242
  6. Chang, V., Xu, Q. A., Chidozie, A., & Wang, H. (2025). Predicting Economic Trends and Stock Market Prices with Deep Learning and Advanced Machine Learning Techniques. Electronics, 13(17), 3396. https://doi.org/10.3390/electronics13173396
  7. Chen, W., Yan, B., Lian, G. and Zhang, Y. (2016). Numerically pricing American options under the generalized mixed fractional Brownian motion model, Physica A: Statistical Mechanics and its Applications.451, 180-189.
  8. Clegg G. (2006), A Practical guide to measuring the Hurst parameter. International journal of simulation: System Science and technology, 7(2):3-14.
  9. Desi E. and Goldberg,2022, “Genetic algorithms in search, optimization, and machine learning,” Queen's University Belfast, vol. 90, no. 2, pp. 12–14
  10. Farida Agustini, (2018), Stock price prediction using geometric Brownian motion, Juornal aof Phys., Conf. Ser. 974 012047
  11. Jamali, H.; Chihab, Y.; García-Magariño, I.; Bencharef, O. Hybrid Forex prediction model using multiple regression, simulated annealing, reinforcement learning and technical analysis. Int. J. Artif. Intell. ISSN 2023, 2252, 8938
  12. Maganini, N, D., Da Silva and Lima F. (2018). Investigation of Multi-fractality in the Brazilian stock market, Physica A. Statistical Mechanics and its Applications, 497,258-271
  13. Murshed, B.A.H.; Al-Ariki, H.D.E.; Mallappa, S. Semantic Analysis Techniques using Twitter Datasets on Big Data: Comparative Analysis Study. Comput. Syst. Sci. Eng. 2020, 35, 495–512.
  14. Rao, B., (2016) Pricing geometric Asian power options under mixed fractional Brownian motion environment. Physica: Statistical Mechanics and its Applications.446, 92-99.
  15. Rouf, N.; Malik, M.B.; Arif, T.; Sharma, S.; Singh, S.; Aich, S.; Kim, H.-C. Stock Market Prediction Using Machine Learning Techniques: A Decade Survey on Methodologies, Recent Developments, and Future Directions. Electronics 2021, 10, 2717. https://doi.org/10.3390/ electronics10212717
  16. Škrinjari´c, T.; Quintino, D.; Ferreira, P. Transfer Entropy Approach for Portfolio Optimization: An Empirical Approach for CESEE