Jesse Schmolze

Junior at UW-Madison studying Economics, Mathematics, and Physics. My research sits at the intersection of machine learning, econometrics, and applied physics, with a focus on finance and economic methodology.

Research

Publication expected within 1-2 months  ·  Extension planned late 2026  ·  Accepted: UW-Madison Undergraduate Research Symposium (Apr 2026)  ·  ASA Midwest Regional Conference on Data Science and Statistics (May 2026)

Learning Interpretable Time-Inhomogeneous Markov Chains via Deep Learning

Machine Learning  ·  Stochastic Processes  ·  Quantitative Finance

This paper develops a neural network framework for modeling the dynamics of equity returns as a time-inhomogeneous Markov chain, estimating regime-dependent transition matrices as a function of macroeconomic and fundamental signals. The approach addresses the well-documented failure of the standard Markov property in financial time series, offering a flexible and interpretable alternative to static transition models. A theoretical and empirical extension is planned for late 2026 or early 2027.

Working paper in 1 month  ·  Publication to follow

Institutions, Networks, and Growth: Estimating Heterogeneous Spillover Transmission via Double Machine Learning

Econometrics  ·  International Macroeconomics  ·  Causal Inference

This paper uses Double Machine Learning on a panel of 120 countries from 1996 to 2023 to estimate how a receiving country's political stability moderates its absorption of exogenous growth shocks transmitted through bilateral trade networks. Instrumenting via Leave-i-Out and commodity terms-of-trade shocks provides causal evidence that the absorption rate is near zero for politically unstable countries and approaches one-to-one for the most stable, with the baseline DML estimates shown to be a conservative lower bound.

Working paper by end of summer  ·  Publication expected winter / spring 2027

Autonomous Race Strategy via Reinforcement Learning: Badger Solar Racing

Reinforcement Learning  ·  Applied Physics  ·  Optimization

This project develops a real-time race strategy system for a competitive solar car in the American Solar Challenge, a ten-day, 1,000-mile cross-country race. A Proximal Policy Optimization agent is trained on a neural network surrogate of a high-fidelity MATLAB/Simulink vehicle simulation, learning to issue speed commands every five minutes that maximize distance while keeping the battery alive across a full race day.

Contact

Open to research collaborations! Email is the fastest way to reach me.