A Comparative Theoretical Study of Option Pricing Models: From the Black-Scholes Framework to Fintech-Enhanced Approaches

Abstract

: A central feature of contemporary capital markets is their capacity to transfer and reallocate risk through options for hedging, speculation, and price discovery. As a result, option prices embed information about future uncertainty through valuation models that link observable market inputs to contingent payoffs. Traditional academic frameworks, most prominently the Black – Scholes model and its extensions, derive closed-form or semi-closed-form prices under idealized assumptions such as frictionless markets, continuous trading, log-normal asset returns, and constant or parametrically specified volatility dynamics. However, real-world markets exhibit volatility smiles and skews, price jumps, microstructure frictions, regime shifts, and heterogeneous data structures that violate these assumptions. In response, recent advances in financial technology have introduced data-intensive and computationally sophisticated approaches, including machine learning, deep learning, and high-performance simulation techniques, which infer pricing relationships non-parametrically from large panels of option prices and state variables. Option pricing can therefore be viewed as a trade-off among pricing accuracy, model stability, interpretability, arbitrage consistency, computational latency, and data requirements. Within this context, conventional structural models, data-driven methods, and hybrid frameworks that combine economic constraints with flexible learning architectures are increasingly evaluated for practical pricing and risk management applications.