Deep Learning Model for Option Pricing - Review

The Indian options market and in particular, the National Stock Exchange (NSE) segment of this marketspace poses a number of challenges when it comes to pricing option trades under high volatility regimes, low liquidity environments as driven by retail volume traders/ long positions and also rapidly changing regulatory ecosystems amongst others. These dynamics are often not captured by traditional pricing models such as the Black-Scholes model, therefore leading to inefficiencies in their prices. Deep learning, which can capture the non-linearities in data and handle quite a large set of features backed by parallel processing power promises to fill that void. There are several factors that any valid pricing model will have to take into account. These factors are underlying asset, strike price, time to expiration, volatility, interest rates, expected dividends and still there is a lot need in order to be able simulate option prices. which then encompass their significance when pricing an option. Furthermore, given their ability to integrate real-time market data (incorporating the India VIX), liquidity measures and economic indicators, these models can tackle some of the shortcomings that plague conventional methodologies. The other ultimate tools to achieve this goal are Option Greeks which plays a very important role in Options Pricing & Risk Management. This paper presents a detailed literature review of latest deep learning architectures applied on option pricing. This study addresses these issues while also bringing novel contributions to an important area of research that has not received attention yet, e.g., market specific models nuanced with the Indian scenario and necessity for a hybrid deep learning approach combining state-of-the-art volatility forecasting alongside data driven methods.