Federico Garza and Max Mergenthaler Canseco on Nixtla’s suite of popular tools for state-of-the-art forecasting.
Subscribe: Apple • Spotify • Stitcher • Google • AntennaPod • Podcast Addict • RSS.
Federico Garza and Max Mergenthaler Canseco are both CTOs and co-founders of Nixtla, a startup building developer-friendly software that helps data scientists deploy predictive pipelines. We discuss time series modeling in general, and the current state of their impressive roster of open source projects including:
Subscribe to the Gradient Flow Newsletter.
Highlights in the video version:
- Nixtla Libraries: origin story and core features
Target users
State of AutoML for time series data
Neural networks and time series
Popular uses cases for Nixtla’s libraries
Adding new algorithms and new models
Tools for productionizing time series models
Nixtla Libraries: difference between open source and commercial offerings
Related content:
- A video version of this conversation is available on our YouTube channel.
- Trends and Opportunities in Time Series
- Aadyot Bhatnagar (of Merlion): Machine Learning for Time Series Intelligence
- Reza Hosseini and Albert Chen (of Greykite): Building a flexible, intuitive, and fast forecasting library
- Sean Taylor (of Prophet): Changes to the data science role and to data science tools
- Sercan Arik: Neural Models for Tabular Data
- Murat Özbayoğlu: Financial Time Series Forecasting with Deep Learning
- Previous podcast episodes pertaining to time series and forecasting.
If you enjoyed this episode, please support our work by encouraging your friends and colleagues to subscribe to our newsletter:
[Image: Time series evolution by Ben Lorica, generated with images from PublicDomainPictures and Pxhere.]