EconPapers    
Economics at your fingertips  
 

Domain Knowledge Preservation in Financial Machine Learning: Evidence from Autocallable Note Pricing

Mohammed Ahnouch (), Lotfi Elaachak and Erwan Le Saout
Additional contact information
Mohammed Ahnouch: PRISM Sorbonne, Université Paris 1 Panthéon-Sorbonne, 17 rue de la Sorbonne, 75005 Paris, France
Lotfi Elaachak: Computer Science and Smart Systems, Faculté des Sciences et Techniques de Tanger, University Abdelmalek Essaadi, Tangier 90000, Morocco
Erwan Le Saout: PRISM Sorbonne, Université Paris 1 Panthéon-Sorbonne, 17 rue de la Sorbonne, 75005 Paris, France

Risks, 2025, vol. 13, issue 7, 1-15

Abstract: Machine learning applications in finance commonly employ feature decorrelation techniques developed for generic statistical problems. We investigate whether this practice appropriately addresses the unique characteristics of financial data, where correlations often encode fundamental economic relationships rather than statistical noise. Using autocallable structured notes as a laboratory, we demonstrate that preserving natural financial correlations outperforms conventional orthogonalization approaches. Our analysis covers autocallable notes with quarterly coupon payments, dual barrier structure, and embedded down-and-in up-and-out put options, priced using analytical methods with automatic differentiation for Greeks’ computation. Across neural networks, gradient boosting, and hybrid architectures, basic financial features achieve superior performance compared to decorrelated alternatives, with RMSE improvements ranging from 43% to 191%. The component-wise analysis reveals complex interactions between autocall mechanisms and higher-order sensitivities, particularly affecting vanna and volga patterns near barrier levels. These findings provide empirical evidence that financial machine learning benefits from domain-specific feature engineering principles that preserve economic relationships. Across all tested architectures, basic features consistently outperformed orthogonalized alternatives, with the largest improvements observed in CatBoost.

Keywords: financial machine learning; feature engineering; autocallable notes; economic correlations; barrier options; Greeks’ analysis (search for similar items in EconPapers)
JEL-codes: C G0 G1 G2 G3 K2 M2 M4 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-9091/13/7/128/pdf (application/pdf)
https://www.mdpi.com/2227-9091/13/7/128/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jrisks:v:13:y:2025:i:7:p:128-:d:1692697

Access Statistics for this article

Risks is currently edited by Mr. Claude Zhang

More articles in Risks from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().

 
Page updated 2025-07-02
Handle: RePEc:gam:jrisks:v:13:y:2025:i:7:p:128-:d:1692697