نوع مقاله : مقاله پژوهشی
عنوان مقاله English
نویسندگان English
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