AI Stories TimeGPT, Nixtla & Forecasting with Max Mergenthaler #53
Dec 10, 2024
Max Mergenthaler, Co-founder and CEO of Nixtla, shares his journey from philosophy to building innovative forecasting libraries. He discusses founding Nixtla and its popular tools like StatsForecast, MLForecast, and NeuralForecast. The conversation highlights TimeGPT, an advanced model for time series analysis, emphasizing its potential over traditional methods. Max also touches on best practices and common pitfalls in forecasting, along with the evolving role of data scientists in this rapidly changing field.
AI Snips
Chapters
Transcript
Episode notes
Nixtla's Origin
- Nixtla originated from Max and his co-founders' work at Orax, a demand forecasting startup.
- They saw the need for a better time series ecosystem and built Nixtla's open-source libraries.
Nixtla's Library Approach
- Nixtla offers separate libraries (StatsForecast, MLForecast, NeuralForecast) for different forecasting approaches.
- This caters to various needs and avoids endorsing a single research direction.
TimeGPT's Promise
- Nixtla's TimeGPT, a commercial foundation model, offers faster and easier time series forecasting.
- Train a large model once, then use it for different forecasting tasks, including zero-shot predictions.