talk-data.com

Forecasting time series can be messy, data is often missing, noisy, or full of structural changes like holidays, outliers, or evolving patterns. This talk shows how to build interpretable time series decomposition models using PyMC, a modern probabilistic programming library.

We’ll break time series into trend, seasonality, and noise components using engineered time features (e.g., Fourier and Radial Basis Functions). You’ll also learn how to model correlated series using hierarchical priors, letting multiple time series "learn from each other." As a case study, we’ll analyze Formula 1 lap time data to compare drivers and explore performance consistency using Bayesian posteriors.

This is a hands-on, code-first talk for data scientists, ML engineers, and researchers curious about Bayesian modeling (or Formula 1). Familiarity with Python and basic statistics is helpful, but no deep knowledge of Bayes is required.

This one-hour tutorial introduces new users to version 5 of PyMC, a powerful Python, open source library for probabilistic programming and Bayesian statistical modeling. Participants will learn the fundamentals of PyMC, best practices for installation and setup, and gain hands-on experience building their first Bayesian model.

Time series data is ubiquitous, from stock market prices and weather patterns to disease outbreaks and sports outcomes. Accurately modeling these data and generating useful predictions requires specialized techniques due to the unique characteristics of time series data. This tutorial provides a practical introduction to Bayesian time series analysis using PyMC, a powerful probabilistic programming library in Python. Participants will learn how to build, evaluate, and interpret various Bayesian time series models, including ARIMA models, dynamic linear models, and stochastic volatility models. We'll emphasize practical application, covering data preprocessing, model selection, diagnostics, and forecasting, empowering attendees to tackle real-world time series problems with confidence.

We talked about:

Rob’s background Going from software engineering to Bayesian modeling Frequentist vs Bayesian modeling approach About integrals Probabilistic programming and samplers MCMC and Hakaru Language vs library Encoding dependencies and relationships into a model Stan, HMC (Hamiltonian Monte Carlo) , and NUTS Sources for learning about Bayesian modeling Reaching out to Rob

Links:

Book 1: https://bayesiancomputationbook.com/welcome.html Book/Course: https://xcelab.net/rm/statistical-rethinking/

Free ML Engineering course: http://mlzoomcamp.com Join DataTalks.Club: https://datatalks.club/slack.html Our events: https://datatalks.club/events.html

Outline: The Bayesian framework; Probabilistic programming; Creating scientific software packages; PyMC.

🎙️ Speaker: Robert Ness \| ⏰ Time: 17:00 UTC / 9am PT / 12pm ET / 6pm Berlin

Graphical causal inference and probabilistic programming share much history. For example, directed probabilistic graphical models were early versions of causal models and d-separation (graphical criteria for conditional independence) provided fundamentals for the do-calculus. Also, directed graphical models drove advancements in Bayesian inference algorithms and were the precursors of probabilistic programming languages like PyTorch. Further, both causal models and probabilistic programming favor explicitly modeling the data generating process. Yet, despite these commonalities, graphical causal inference and probabilistic programming have evolved into separate communities with little cross-talk beyond Bayesian inference of parameters in causal estimators. In this seminar, we discuss how to do causal graphical modeling with probabilistic programming, as well as tools and design patterns for doing so.

📑 Resources

• Causal AI Book: https://www.manning.com/books/causal-ai
• Related Paper: https://arxiv.org/abs/2102.06626
• Probabilistic Machine Learning Workshop: https://www.altdeep.ai/p/probml
• Causal Modeling in Machine Learning Workshop: https://www.altdeep.ai/p/causalml

📜 Outline of Talk / Agenda:

• 5 min: Intro to PyMC Labs and speakers
• 45 min: Presentation, panel discussion
• 10 min: Q&A

💼 About the speaker:

1. Robert Ness

Researcher at Microsoft Research, where he focuses on causal reasoning, deep probabilistic modeling, language models and programming languages. He is author of the book Causal AI, and founder of AI learning platform Altdeep.ai. He has worked as a research engineer and received his Ph.D. in statistics from Purdue University. He is a Johns Hopkins SAIS alumnus.

🔗 Connect with Robert Ness: 👉 LinkedIn: https://www.linkedin.com/in/osazuwa/ 👉 Twitter: https://twitter.com/osazuwa 👉 GitHub: https://github.com/altdeep/causalML 👉 MSR: https://www.microsoft.com/en-us/research/people/robertness/

💼 About the Host:

1. Dr. Thomas Wiecki (PyMC Labs)

Dr. Thomas Wiecki is an author of PyMC, the leading platform for statistical data science. To help businesses solve some of their trickiest data science problems, he assembled a world-class team of Bayesian modelers and founded PyMC Labs -- the Bayesian consultancy. He did his PhD at Brown University studying cognitive neuroscience.

🔗 Connect with Thomas Wiecki: 👉 Website: https://www.pymc-labs.com/ 👉 GitHub: https://github.com/twiecki 👉 Twitter: https://twitter.com/twiecki 👉 Blog posts: https://twiecki.io/

📖 Code of Conduct: Please note that participants are expected to abide by PyMC's Code of Conduct.

🔗 Connecting with PyMC Labs: 👥 LinkedIn: https://www.linkedin.com/company/pymc-labs/ 🐦 Twitter: https://twitter.com/pymc_labs 🎥 YouTube: https://www.youtube.com/c/PyMCLabs 🤝 Meetup: https://www.meetup.com/pymc-labs-online-meetup/

🔗 Connecting with PyMC Open Source: 💬 Q&A/Discussion: https://discourse.pymc.io 🐙 GitHub: https://github.com/pymc-devs/pymc 💼 LinkedIn: https://www.linkedin.com/company/pymc/mycompany 🐥 Twitter: https://twitter.com/pymc_devs 📺 YouTube: https://www.youtube.com/c/PyMCDevelopers 🎉 Meetup: https://www.meetup.com/pymc-online-meetup/

🎙️ Speaker: Daniel Lee\, Thomas Wiecki \| ⏰ Time: 16:00 UTC / 9am PT / 12pm ET / 6pm Berlin

This will be a high-level talk discussing the separation of statistical models and inference algorithms.

Things we’d like to talk about:

• The general vernacular combines two concepts together: model + inference. But they can be thought of separately.
• Given a statistical model, there are (at least) 3 different types of inference. Optimization, approximate inference, Bayesian inference. We’ll talk about some of the use cases of each. And where stochastic optimization fits in.
• A description of GPTs and how it can be implemented in Stan (and similarly in PyMC or any other PPL).

This talk won’t be overly technical. The goal will be to try to solidify the differences between the different types of inference and when to apply them. There will be plenty of time for Q&A.

📜 Outline of Talk / Agenda:

• 5 min: Intro to PyMC Labs and speakers
• 45 min: Presentation, panel discussion
• 10 min: Q&A

💼 About the speaker:

1. Daniel Lee Daniel Lee is at Zelus Analytics working on player projection models across multiple sports. Daniel is a computational Bayesian statistician who helped create and develop Stan, the open-source statistical modeling language with over 20 years of experience in numeric computation and software; over 10 years of experience creating and working with Stan; and 5 years working on pharma-related models including joint models for estimating oncology treatment efficacy and PK/PD models. Past projects have covered estimating vote share for state and national elections; clinical trials for rare diseases and non-small-cell lung cancer; satellite control software for television and government; retail price sensitivity; data fusion for U.S. Navy applications; sabermetrics for an MLB team; and assessing “clutch” moments in NFL footage. He holds a B.S. in Mathematics with Computer Science from MIT, and a Master of Advanced Studies in Statistics from Cambridge University.

🔗 Connect with Daniel Lee: 👉 LinkedIn: https://www.linkedin.com/in/syclik/ 👉 Twitter: https://twitter.com/djsyclik 👉 GitHub: https://github.com/syclik 👉 Website: https://syclik.com/ 👉 Blog: https://medium.com/@bayesianops

1. Dr. Thomas Wiecki (PyMC Labs) Dr. Thomas Wiecki is an author of PyMC, the leading platform for statistical data science. To help businesses solve some of their trickiest data science problems, he assembled a world-class team of Bayesian modelers and founded PyMC Labs -- the Bayesian consultancy. He did his PhD at Brown University studying cognitive neuroscience.

🔗 Connect with Thomas Wiecki: 👉 GitHub: https://github.com/twiecki 👉 Twitter: https://twitter.com/twiecki 👉 Website: https://twiecki.io/

📖 Code of Conduct: Please note that participants are expected to abide by PyMC's Code of Conduct.

🔗 Connecting with PyMC Labs: 👥 LinkedIn: https://www.linkedin.com/company/pymc-labs/ 🐦 Twitter: https://twitter.com/pymc_labs 🎥 YouTube: https://www.youtube.com/c/PyMCLabs 🤝 Meetup: https://www.meetup.com/pymc-labs-online-meetup/

🔗 Connecting with PyMC Open Source: 💬 Q&A/Discussion: https://discourse.pymc.io 🐙 GitHub: https://github.com/pymc-devs/pymc 💼 LinkedIn: https://www.linkedin.com/company/pymc/mycompany 🐥 Twitter: https://twitter.com/pymc_devs 📺 YouTube: https://www.youtube.com/c/PyMCDevelopers 🎉 Meetup: https://www.meetup.com/pymc-online-meetup/

🎙️ Speaker: Maxim Kochurov \| ⏰ Time: 9am PT / 12pm ET / 6pm Berlin

State of Bayes is a series of webinars about advances in practical methods and modeling intuition. The major focus of the webinar series will be on understanding concepts of advanced statistical models and introducing prior knowledge into the loop. This free course will be interesting for Bayesian practitioners who want to deepen their understanding about Bayesian modeling.

In the closing webinar session we'll meet Gaussian processes for time series analysis. There are some very enlightening applications that bring GP to the number one most useful models in practice:

• Most known are seasonality decompositions for time series.
• Less known but very useful is time varying parameter for a model (an example of that you can see here: https://www.pymc-labs.io/blog-posts/modelling-changes-marketing-effectiveness-over-time/)

During the webinar we'll get familiar with necessary concepts to apply a GP on a time series. At the coding session we'll revisit Rolling regression example from pymc-examples and will make that even more cool than ever before.

• Subscribe to our PyMCLabs YouTube to see past videos.
• Feedback Form: https://forms.gle/xHsaVzWrzDxRjhrt5

Sessions (generally bi-weekly) The full course is:

• Session 1️⃣: Introduction ▶️ L1: VIDEO
• Session 2️⃣: Bayesian Thinking ▶️ L2: VIDEO
• Session 3️⃣: Hierarchical modeling ▶️ L3: VIDEO
• Session 4️⃣: Interpretable Linear Regressions ▶️ L4: VIDEO
• Session 5️⃣: Bayesian AB testing ▶️ L5: VIDEO
• Session 6️⃣: Gaussian Processes ▶️ L6:VIDEO
• Session 7️⃣: Gaussian Processes for Time Series (6th July)

💼 About the speaker:

1. Maxim Kochurov Maxim is a core developer of PyMC, a probabilistic programming language. Since the foundation of PyMC Labs he helps to improve complex statistical models and create a reusable solution. Besides strong expertise in Bayesian modeling his background includes economics, software engineering, and large-scale computer vision.

🔗 Connect with Maxim: 👉 LinkedIn: https://www.linkedin.com/in/ferrine 👉 Twitter: https://twitter.com/ferrine96 👉 GitHub: https://github.com/ferrine 👉 Website: https://ferrine.github.io

📖 Code of Conduct: Please note that participants are expected to abide by PyMC's Code of Conduct.

🔗 Connecting with PyMC Labs: 👥 LinkedIn: https://www.linkedin.com/company/pymc-labs/ 🐦 Twitter: https://twitter.com/pymc_labs 🎥 YouTube: https://www.youtube.com/c/PyMCLabs 🤝 Meetup: https://www.meetup.com/pymc-labs-online-meetup/

🔗 Connecting with PyMC Open Source: 💬 Q&A/Discussion: https://discourse.pymc.io 🐙 GitHub: https://github.com/pymc-devs/pymc 💼 LinkedIn: https://www.linkedin.com/company/pymc/mycompany 🐥 Twitter: https://twitter.com/pymc_devs 📺 YouTube: https://www.youtube.com/c/PyMCDevelopers 🎉 Meetup: https://www.meetup.com/pymc-online-meetup/

🎙️ Speaker: Maxim Kochurov \| ⏰ Time: 9am PT / 12pm ET / 6pm Berlin

Gaussian Processes are probably the most powerful models you can encounter in Bayesian statistics. To apply them, you first need to get familiar with the basics and first principles. While complicated formulas are awesome, we'll more focus on intuition and possible applications. In this lesson, you'll know

• what is a kernel
• how to think about kernel parameters
• how to make gaussian process hierarchy

And a bonus, we'll lead a coding session where we apply a Gaussian process to analyze unbalanced stratified poll data.

State of Bayes is a series of webinars about advances in practical methods and modeling intuition. The major focus of the webinar series will be on understanding concepts of advanced statistical models and introducing prior knowledge into the loop. This free course will be interesting for Bayesian practitioners who want to deepen their understanding about Bayesian modeling.

• Subscribe to our PyMCLabs YouTube to see past videos.
• Feedback Form: https://forms.gle/xHsaVzWrzDxRjhrt5

Sessions (generally bi-weekly) The full course is:

• Session 1️⃣: Introduction ▶️ L1: VIDEO
• Session 2️⃣: Bayesian Thinking ▶️ L2: VIDEO
• Session 3️⃣: Hierarchical modeling ▶️ L3: VIDEO
• Session 4️⃣: Interpretable Linear Regressions ▶️ L4: VIDEO
• Session 5️⃣: Bayesian AB testing ▶️ L5: VIDEO
• Session 6️⃣: Gaussian Processes (22th June, 2023)
• Session 7️⃣: Gaussian Processes for Time Series

💼 About the speaker:

1. Maxim Kochurov Maxim is a core developer of PyMC, a probabilistic programming language. Since the foundation of PyMC Labs he helps to improve complex statistical models and create a reusable solution. Besides strong expertise in Bayesian modeling his background includes economics, software engineering, and large-scale computer vision.

🔗 Connect with Maxim: 👉 LinkedIn: https://www.linkedin.com/in/ferrine 👉 Twitter: https://twitter.com/ferrine96 👉 GitHub: https://github.com/ferrine 👉 Website: https://ferrine.github.io

📖 Code of Conduct: Please note that participants are expected to abide by PyMC's Code of Conduct.

🔗 Connecting with PyMC Labs: 👥 LinkedIn: https://www.linkedin.com/company/pymc-labs/ 🐦 Twitter: https://twitter.com/pymc_labs 🎥 YouTube: https://www.youtube.com/c/PyMCLabs 🤝 Meetup: https://www.meetup.com/pymc-labs-online-meetup/

🔗 Connecting with PyMC Open Source: 💬 Q&A/Discussion: https://discourse.pymc.io 🐙 GitHub: https://github.com/pymc-devs/pymc 💼 LinkedIn: https://www.linkedin.com/company/pymc/mycompany 🐥 Twitter: https://twitter.com/pymc_devs 📺 YouTube: https://www.youtube.com/c/PyMCDevelopers 🎉 Meetup: https://www.meetup.com/pymc-online-meetup/