Bayesian hierarchical time series with Prophet and PyMC3 - Matthijs Brouns | PyData Jeddah

When doing time-series modeling, you often end up in a situation where you want to make long-term predictions for multiple related time series. In this talk, we’ll see how we can combine the ideas behind Bayesian hierarchical models and Facebook's Prophet package to do exactly that. Resources: 1. Presentation slides: https://drive.google.com/file/d/19ucW8AotBupHPq6BybxFbpUi-Q0ngXHm/view 2. Timeseers code in Github: https://github.com/MBrouns/timeseers Timestamps: 0:00 - Intro 2:16 - About PyData Global Conference 3:32 - What is Prophet? 10:57 - Dealing with trends 14:21 - Linear trends in Prophet 16:19 - Linear trends in PyMC3 notebook 26:28 - Fourier seasonality 28:21 - Fourier seasonality in Prophet 29:09 - Fourier seasonality in PyMC3 notebook 35:26 - Prophet API 41:12 - Demo: Build a custom component using PyMC3 notebook 52:06 - Intro to Bayesian hierarchical models 1:08:00 - Q&A Guest speaker: Matthijs Brouns - https://www.linkedin.com/in/mbrouns/ www.pydata.org PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R. PyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome! 00:10 Help us add time stamps or captions to this video! See the description for details. Want to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps