In this paper, we explore the feasibility of using machine learning algorithms to identify options trading at a discount or premium based on historical company-specific and macroeconomic data. We challenge the notion that efficient markets make it impossible to consistently achieve abnormal returns when investing. Our analysis compares the performance of our best model against two benchmarks: random selection of options and selecting options based on previous volatility. Our findings indicate

In this paper, we explore the feasibility of using machine learning algorithms to identify options trading at a discount or premium based on historical company-specific and macroeconomic data. We challenge the notion that efficient markets make it impossible to consistently achieve abnormal returns when investing. Our analysis compares the performance of our best model against two benchmarks: random selection of options and selecting options based on previous volatility. Our findings indicate that selections based on our model inconsistently outperform random selection, whilst it consistently outperforms the previous volatility benchmark. Overall, there is not enough evidence to support the consistent outperforming of the market by our model.