Option Pricing Based on Implied Volatility Forecasting and No-Arbitrage Projection Correction: Evidence from SSE 50ETF Options

DOI

10.2991/978-94-6239-801-6_37How to use a DOI?

Keywords

Option Pricing; Implied Volatility Forecasting; XGBoost; No-Arbitrage Projection

Abstract

As option markets expand, pricing and risk assessment grow increasingly critical for investor decisions and price discovery. In practice, predictive accuracy and no-arbitrage constraints are often hard to satisfy simultaneously. Using SSE 50ETF options as samples, this paper proposes a two-stage prediction-projection framework. First, XGBoost is applied in the implied volatility space to learn the volatility surface shape, followed by rigorous out-of-sample prediction. Predicted implied volatilities are deterministically mapped to option prices via the Black-Scholes model to generate a price surface. In the price space, projection corrections are imposed on three static no-arbitrage conditions via minimizing squared deviations from predicted prices. Empirical results show implied volatility prediction errors are broadly stable, with no noticeable increase after price mapping. However, point predictions alone lead to clear no-arbitrage violations, which are mostly eliminated after correction, accompanied by reduced pricing errors. Further one-day Delta hedging tests reveal that for highly liquid samples, corrected hedging performance outperforms prediction-only results, indicating the correction ensures constraint compliance and more stable risk measurement. Robustness checks confirm the conclusion’s reliability. This paper develops an intuitive framework integrating statistical prediction with financial constraints and proposes an embeddable quality-control scheme for pricing and risk-management systems.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Manyi Liu
PY  - 2026
DA  - 2026/10/23
TI  - Option Pricing Based on Implied Volatility Forecasting and No-Arbitrage Projection Correction: Evidence from SSE 50ETF Options
BT  - Proceedings of the 2026 2nd International Conference on Financial Innovation and Marketing Management (FIMM 2026)
PB  - Atlantis Press
SP  - 330
EP  - 339
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6239-801-6_37
DO  - 10.2991/978-94-6239-801-6_37
ID  - Liu2026
ER  -