Random Forest In Options Pricing
Session Number
Project ID: CMPS 12
Advisor(s)
Ellen Taylor-Lubrano, CBOE Global Markets
Discipline
Computer Science
Start Date
17-4-2024 9:20 AM
End Date
17-4-2024 9:35 AM
Abstract
The main objective of this research was to explore the integration of machine learning algorithms, particularly the Random Forest Regressor model utilizing decision trees, in enhancing the Black-Scholes Model for options pricing within the financial industry. Machine learning is becoming more prevalent in the financial sector, so this research gives more insight into how it is directly applicable in the derivative market. Once the model was trained and tested on a 2013 data set, the random forest model yielded a residual squared value of 0.97. This indicates that the model is mostly accurate in predicting the options price from that data set. The quality of the model depends entirely on the quality of its data, so the next steps would be to collect more real time data and train the model. This model offers the advantages of the traditional Black- Scholes equation while also addressing its limitations. Unlike the Black-Scholes model, it considers various factors such as both European and American options, doesn't assume constant volatility, and could provide flexibility with cash flow by incorporating dividend values from additional datasets as input.
Random Forest In Options Pricing
The main objective of this research was to explore the integration of machine learning algorithms, particularly the Random Forest Regressor model utilizing decision trees, in enhancing the Black-Scholes Model for options pricing within the financial industry. Machine learning is becoming more prevalent in the financial sector, so this research gives more insight into how it is directly applicable in the derivative market. Once the model was trained and tested on a 2013 data set, the random forest model yielded a residual squared value of 0.97. This indicates that the model is mostly accurate in predicting the options price from that data set. The quality of the model depends entirely on the quality of its data, so the next steps would be to collect more real time data and train the model. This model offers the advantages of the traditional Black- Scholes equation while also addressing its limitations. Unlike the Black-Scholes model, it considers various factors such as both European and American options, doesn't assume constant volatility, and could provide flexibility with cash flow by incorporating dividend values from additional datasets as input.