Master Thesis: Limit order placement with Reinforcement Learning
-
Updated
Jan 9, 2026 - Jupyter Notebook
Master Thesis: Limit order placement with Reinforcement Learning
Governance‑aware AI enablement lab. Operationalizes PM insights into working agents and prompt libraries that surface delivery, governance, and compliance risks before scaling analytics or AI systems.
An intelligent Reinforcement Learning based trade execution engine trained on real SPY 1-minute data to minimize market impact and cost. Uses PPO in a custom Gym environment to dynamically decide execution quantities and outperforms traditional TWAP/VWAP strategies.
To associate your repository with the execution-strategy topic, visit your repo's landing page and select "manage topics."