Nonlinear pricing kernels via neural networks
-
- 0 Rating
- 0 Reviews
- 4 Students Enrolled
Nonlinear pricing kernels via neural networks
Neural networks are used to estimate nonlinear stochastic discount factors, improving asset pricing performance and ESG factor significance.
-
- 0 Rating
- 0 Reviews
- 4 Students Enrolled
Requirements
- Asset Pricing, Neural Networks, ESG, Pricing Kernel, Deep Learning, Financial Econometrics
General Overview
Description
This study develops a nonlinear asset pricing model using feedforward neural networks (MLPs) to approximate the stochastic discount factor (SDF). The neural network-based pricing kernel satisfies admissibility conditions and captures nonlinearities and high-dimensional effects, including ESG variables. Model selection and specification tests confirm that neural models outperform linear and elastic net alternatives, especially in out-of-sample pricing errors and Sharpe ratios. Significance tests show most ESG factors contribute meaningfully to pricing, with robustness verified across various test asset sets. Methodologies include block bootstrap testing, Hansen-Jagannathan distance minimization, and factor importance ranking.
Recommended for you
Meet the instructors !
David Siang-Li Jheng is a PhD candidate at the Doctoral School of Cybernetics and Economic Statistics, Bucharest University of Economic Studies, Romania. His research focuses on detecting anomalies and modeling dependence structures in high-dimensional, high-frequency financial data.
With a background in financial engineering and mathematics from National Yang Ming Chiao Tung University (NYCU) and National Taiwan Normal University (NTNU), he investigates systemic risks through advanced methodologies such as Financial Risk Meters and anomaly detection models.