Podcast
Algorithmic Trading with Python: Backtesting, Risk Management and Deployment
Open original DataTalks.Club episode
Algorithmic Trading with Python: Backtesting, Risk Management and Deployment
Original Episode
Use these links for the canonical episode and media sources.
- Open the original DataTalks.Club podcast page
- Watch on YouTube
- Listen on Spotify
- Listen on Apple Podcasts
Episode Overview
How do you turn a trading idea into a robust, risk-managed algorithm in Python? In this episode Ivan Brigida — analytics lead behind PythonInvest with 10+ years in statistical modeling, forecasting, econometrics and finance — walks through practical steps for algorithmic trading with Python, from data sourcing to deployment (and a clear reminder this is educational, not investment advice).
People
Use these links to connect the episode to guest notes.
Chapter Summary
Use these checkpoints to decide whether to open the source transcript.
- 0:00 - Podcast Introduction
- 1:35 - Guest Introduction: Ivan Brigida — Analytics Lead & PythonInvest
- 2:08 - Disclaimer: Financial discussion, not investment advice
- 3:53 - Background & career trajectory from finance to analytics
- 6:42 - Google experience and role transitions
- 7:29 - Choosing individual contributor work over people management
- 9:25 - Investing interest: economics education to practical trading
- 11:47 - Blogging & building a pet project to test strategies
- 13:15 - Financial data sources and APIs for retail investors (Yahoo, Quandl, Polygon)
- 15:23 - Market data format explained: OHLCV time series
- 18:39 - Adjusted close and data quality considerations
- 19:47 - Mean reversion strategy: concept and application
- 22:14 - Risk management fundamentals and stop-loss thresholds
- 26:48 - Backtesting methodology and avoiding time-series data leakage
- 29:44 - Walk-forward simulation: weekly predictions and selection rules
- 35:15 - Trade execution and position sizing for algorithmic strategies
- 38:24 - Discipline: sticking to strategy vs emotional trading
- 40:51 - Evaluation metrics: ROI, precision focus, and trading fees impact
- 43:39 - Prediction target definition: binary growth thresholds (e.g., 5%)
- 45:55 - Feature engineering: time-window stats and handcrafted indicators
- 48:02 - Model choices: logistic regression, XGBoost, NN for stock prediction
- 49:58 - Explainability: feature importance and model debugging
- 51:46 - Deployment options: cron, Airflow, APIs and partial automation
- 55:05 - Learning pathways: MLOps, ML Zoomcamp, and practical projects
- 57:29 - PythonInvest content: API guides, models, portfolio allocation stories
- 1:01:06 - Course plans, sign-up, and community building