American option pricing with machine learning: An extension of the Longstaff-Schwartz method

Pricing American options accurately is of great theoretical and practical importance. We propose using machine learning methods, including support vector regression and classification and regression trees. These more advanced techniques extend the traditional Longstaff-Schwartz approach, replacing the OLS regression step in the Monte Carlo simulation. We apply our approach to both simulated data and market data from the S&P 500 Index option market in 2019. Our results suggest that support vector regression can be an alternative to the existing OLS-based pricing method, requiring fewer simulations and reducing the vulnerability to misspecification of basis functions.

The application of the improved option parity arbitrage model in SSE 50ETF option

The SSE 50ETF option is China's first stock index option product launched in 2015. For a number of reasons, the options market can sometimes create arbitrage opportunities. Based on the theory of option parity arbitrage and taking into account the transaction costs, this paper explores effective options arbitrage strategies and practices them. Based on the theory of option parity arbitrage and taking into account the transaction costs, this paper establishes an effective option arbitrage strategy model and puts it into practice. The results show that there are indeed arbitrage opportunities in the market that exceed the risk-free rate of return, but there are not many such opportunities, and there is not much arbitrage space under many opportunities. This is not only the embodiment of high market efficiency, but also the result of taking various transaction costs into full consideration in this paper to ensure the effectiveness of arbitrage.