Blanka Horvath

Blanka Horvath is a researcher focused on quantitative finance and machine learning applications in stochastic processes. Her work bridges financial mathematics with computational techniques, emphasizing volatility modeling and neural network applications. She has contributed to the development of deep learning methods for pricing and hedging financial derivatives, as well as analyzing stochastic processes in both financial and biomedical contexts.

Her research interests include stochastic volatility models, rough volatility, and the application of kernel methods to financial time series. She has collaborated on projects involving rough volatility hedging strategies, deep learning for volatility calibration, and the analysis of MRI noise patterns.

Blanka has published extensively in peer-reviewed journals such as Risks and Quantitative Finance, with notable contributions to conferences like NeurIPS. Her work often integrates machine learning with financial engineering, addressing challenges in derivative pricing, risk management, and healthcare imaging analysis.