Managing Quant Experiments with Experiment Manager
Overview
Quantitative research involves running extensive backtests and stability tests to refine trading strategies. Managing these experiments efficiently—tracking tested parameters, handling combinatorial complexity, and ensuring reproducibility—can be challenging.
In this webinar, learn how to streamline quant research using Experiment Manager.
Highlights
We will demonstrate how to:
- Organize and track large-scale parameter scans and stability tests.
- Automate and parallelize backtesting workflows to improve efficiency.
- Evaluate strategy robustness by analyzing parameter sensitivity and asset dependence.
Using a mean-reversion trading strategy implemented in Python, we will walk through setting up experiments, computing performance metrics, and visualizing results. Experiment Manager provides a structured approach to managing quant research, making it easy to optimize hyperparameters, validate strategies, and ensure robustness within the same framework.
About the Presenter
Dr Peter Brady is a Principal Application Engineer with a background in numerical simulation, analysis and high-performance computing Peter covers these areas of the MathWorks products as well as machine learning, deep learning, deployment and cloud as well as computational finance. He has worked with customers across the finance industry in areas for high-speed algorithmic trading, portfolio optimisation and risk management. Peter has a PhD in Mechanical Engineering and a Bachelors in Civil Engineering, both from UTS, and is a Chartered Practicing Engineer with Engineers Australia (CPEng NER).
Product Focus
This event is part of a series of related topics. View the full list of events in this series.
