Hierarchical Forecasting in Python | Nixtla

A vast amount of time series datasets are organized into structures with different levels or hierarchies of aggregation.
In this talk, we introduce the open-source Hierarchical Forecast library, which contains different reconciliation algorithms, preprocessed datasets, evaluation metrics, and a compiled set of statistical baseline models. This Python-based framework aims to bridge the gap between statistical modeling and Machine Learning in the time series field.
ABOUT THE SPEAKER:
Max Mergenthaler is the CEO and Co-Founder of Nixtla, a time-series research and deployment startup. He is also a seasoned entrepreneur with a proven track record as the founder of multiple technology startups. With a decade of experience in the ML industry, he has extensive expertise in building and leading international data teams. Max has also made notable contributions to the Data Science field through his co-authorship of papers on forecasting algorithms and decision theory.
👉 Sign up for our “No BS” Newsletter to get the latest technical data & AI content: datacouncil.ai...
ABOUT DATA COUNCIL:
Data Council (www.datacounci...) is a community and conference series that provides data professionals with the learning and networking opportunities they need to grow their careers.
Make sure to subscribe to our channel for the most up-to-date talks from technical professionals on data related topics including data infrastructure, data engineering, ML systems, analytics and AI from top startups and tech companies.
FOLLOW DATA COUNCIL:
Twitter: / datacouncilai
LinkedIn: / datacouncil-ai

[@tgnbeats]

Amazing Work! Well done to the Nixtla team

[@Darokbr]

I am following this package. Very interesting.

[@IvanRubnenkov]

Can you use hierarchical forecast methods (minTrace, ERM) for multiplicative dependencies between time series, not the additive ones? Thanks in advance

[@TheKinsey06]

I face these exact issues at work. I needed this video

[@FindMultiBagger]

Hirachical forecast is really slow , but hats of statsforecast developers and contributers for ecosystem 🎉 😇♥️

[@gauravsukhadia638]

Hypothetically if I have let's say 4 million skus what do you think how long will it take ?

[@FindMultiBagger]

@@gauravsukhadia638 For me their are 10 Million sku , for 1 million sku it took 3/4 hrs , but their are lots of issues like , historical validation and future forecast. but I able to fix those issue myself. suggestion use OLS method for faster execution MinT is slow

[@Leibniz_28]

Great initiative

[@Alfalphe]

What about Exogenous variables?

[@STEEZEAI]

please if anyone knows how to use exog variables with this, explain how you did it

[@517127]

How acess the residual or rmse for each id?