Abstract
This paper presents a comprehensive examination of model risk within the derivatives pricing context, specifically focusing on autocallable products. It identifies potential sources of model risk, encompassing insufficient model assumptions, calibration challenges, data availability limitations, and overfitting concerns. The paper explores diverse approaches for model risk mitigation in derivatives pricing, including robust model selection, rigorous model validation, risk sensitivity analysis, and model diversification. Moreover, it investigates the utilization of advanced machine learning techniques to alleviate model risk and discusses alternatives to tree methods, such as manifold learning algorithms and topological data analysis, for gaining deeper insights into intricate datasets and pricing relationships. The paper concludes with an analysis of autocallable notes, emphasizing the critical importance of accurately capturing correlations between underlying assets and their corresponding volatilities.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Stress testing is also a regulatory process that assesses the resilience of banks and their ability to withstand adverse economic conditions by subjecting them to hypothetical scenarios. In the Eurozone, stress testing is conducted by the European Central Bank (ECB) and the European Banking Authority (EBA), while in the US, it is overseen by the Federal Reserve, the Office of the Comptroller of the Currency (OCC), and the Federal Deposit Insurance Corporation (FDIC).
- 2.
Tree methods in machine learning, such as decision trees, are algorithms used for predictive modeling based on branching decision-making logic, not to confuse with binomial trees in derivative pricing which are financial models that visualize possible paths for asset prices over time using a binary, branching structure.
- 3.
It is a type of stochastic volatility model which assumes that the volatility of the underlying asset is the product of both a random (stochastic) and a deterministic, function of the underlying, factors.
- 4.
The dependence of the duration of an autocallable note on the level of the underlying asset introduces sensitivity to the correlation between the underlying asset and interest rates, impacting the effectiveness of hedging strategies and overall risk exposure.
References
Arkanuddin, M.F., Saragih, F.D., Nugroho, B.Y.: The key role of the financial regulation in FinTech ecosystem: a model validation. Studi. Appl. Econ. 39, 1–16 (2021)
Bergomi, L.: Stochastic Volatility Modeling (2015)
Biagini, S., Cont, R.: Model-free representation of pricing rules as conditional expectations. In: Stochastic Processes and Applications to Mathematical Finance. World Scientific (2007)
Bouchard, B., Ekeland, I., Touzi, N.: On the Malliavin approach to Monte Carlo approximation of conditional expectations. Finan. Stochast. 8, 45–71 (2004)
Bouzoubaa, M.: Equity Derivatives Explained. Palgrave Macmillan (2014)
Bouzoubaa, M., Osseiran, A.: Exotic Options and Hybrids: A Guide to Structuring, Pricing and Trading. Wiley, Hoboken (2010)
Carlsson, G., Vejdemo-Johansson, M.: Topological Data Analysis with Applications (2021)
Carr, P., Lee, R.: Robust replication of volatility derivatives. In: PRMIA Award for Best Paper in Derivatives, MFA 2008 Annual Meeting (2008)
Christodoulakis, G.A., Satchell, S.: The Analytics of Risk Model Validation. Elsevier (2007)
Cuchiero, C., Khosrawi, W., Teichmann, J.: A generative adversarial network approach to calibration of local stochastic volatility models. Risks 8, 101 (2020)
Daveloose, C., Khedher, A., Vanmaele, M.: Representations for conditional expectations and applications to pricing and hedging of financial products in Lévy and jump-diffusion setting. Stoch. Anal. Appl. 37, 281–319 (2019)
De Col, A., Kuppinger, P.: The interplay between stochastic volatility and correlations in equity autocallables. Available at SSRN 3228065 (2017)
Farkas, W., Ferrari, F., Ulrych, U.: Pricing autocallables under local-stochastic volatility. Front. Math. Finan. 1, 575–610 (2022)
Gholizadeh, S., Zadrozny, W.: A short survey of topological data analysis in time series and systems analysis. arXiv preprint arXiv:180910745 (2018)
Gidea, M., Katz, Y.: Topological data analysis of financial time series: landscapes of crashes. Physica A Stat. Mech. Appl. 49, 820–834 (2018)
Glasserman, P., Xu, X.: Robust risk measurement and model risk. Quant. Financ. 14, 29–58 (2014)
Guo, I., Loeper, G., Wang, S.: Calibration of local-stochastic volatility models by optimal transport. Math. Finan. 32, 46–77 (2022)
Güzel, I., Kaygun, A.: Classification of stochastic processes with topological data analysis. arXiv preprint arXiv:220603973 (2022)
Bartholomew, H., Somasundaram, N., Becker, L.: Natixis’s €260m hit blamed on big books and Kospi3 product. Risknet (2018)
Han, H., Li, W., Wang, J., Qin, G., Qin, X.: Enhance explainability of manifold learning. Neurocomputing 500, 877–895 (2022)
Henry-Labordère, P.: Calibration of local stochastic volatility models to market smiles: a Monte-Carlo approach. Risk Mag. (2009)
Huang, Y.: Manifold learning for financial market visualization. In: Proceedings of the 2020 5th International Conference (2020)
Huang, Y., Kou, G.: A kernel entropy manifold learning approach for financial data analysis. Decis. Support. Syst. 64, 31–42 (2014). https://doi.org/10.1016/j.dss.2014.04.004
Jacobs, M., Karagozoglu, A.K., Sensenbrenner, F.: Stress testing and model validation: application of the Bayesian approach to a credit risk portfolio. J. Risk Model Valid. 9, 41–70 (2015)
Jerbi, Y., Kharrat, M.: Conditional expectation determination based on the J-process using Malliavin calculus applied to pricing American options. J. Stat. Comput. Simul. 84, 2465–2473 (2014)
Kohler, M.: A review on regression-based Monte Carlo methods for pricing American options. In: Devroye, L., Karasözen, B., Kohler, M., Korn, R. (eds.) Recent Developments in Applied Probability and Statistics, pp. 37–58 (2010). https://doi.org/10.1007/978-3-7908-2598-5_2
Kouritzin, M.A., Zeng, Y.: Weak convergence for a type of conditional expectation: application to the inference for a class of asset price models. Nonlinear Anal. Theor. Meth. Appl. 60, 231–239 (2005)
Li, C.: Closed-form expansion, conditional expectation, and option valuation. Math. Oper. Res. 39, 487–516 (2014)
Majumdar, S., Laha, A.K.: Clustering and classification of time series using topological data analysis with applications to finance. Exp. Syst. Appl. 162, 113868 (2020)
Cameron, M.: Uridashi losses put at $500 million after Nikkei rebounds. Risknet (2013)
Stanley, M.: Auto-Callable Yield Notes (2020)
Somasundaram, N.: Natixis said to offload a third of Korean structured book. Risknet (2019)
Currency OOTCOT: Supervisory Guidance on Model Risk Management. OCC 2011–12 (2011)
Salon, G.: Equity autocalls and vanna negative carries: pricing and hedging with a simple add-on. Available at SSRN 3383122 (2019)
Seversky, L.M., Davis, S., Berger, M.: On time-series topological data analysis: new data and opportunities. In: Proceedings of the IEEE (2016)
Currency TOOTCOT: Model Risk Management (2021)
Zeron, M., Wu, M., Ruiz, I.: The FRTB-IMA computational challenge for Equity Autocallables. arXiv preprint arXiv:230506215 (2023)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ahnouch, M., Elaachak, L., Ghadi, A. (2024). Model Risk in Financial Derivatives and The Transformative Impact of Deep Learning: A Systematic Review. In: Ben Ahmed, M., Boudhir, A.A., El Meouche, R., KaraÈ™, Ä°.R. (eds) Innovations in Smart Cities Applications Volume 7. SCA 2023. Lecture Notes in Networks and Systems, vol 938. Springer, Cham. https://doi.org/10.1007/978-3-031-54376-0_14
Download citation
DOI: https://doi.org/10.1007/978-3-031-54376-0_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-54375-3
Online ISBN: 978-3-031-54376-0
eBook Packages: EngineeringEngineering (R0)