Darts for Time Series Forecasting – Julien Herzen, Francesco Lässig at PyData Global 2021

  • by Julien Herzen, Francesco Lässig
  • 28 minutes

Darts for Time Series Forecasting – Julien Herzen, Francesco Lässig at PyData Global 2021

Darts for Time Series Forecasting
Speakers: Julien Herzen, Francesco Lässig

Summary
This talk will give an introduction to Darts (https://github.com/unit8co/darts), an open-source library for time-series processing and forecasting. Darts provides a wide variety of models and tools under a unified and user-friendly API. We will give a high-level introduction to both time series forecasting and the main features of Darts.

Description
Time series are everywhere in science and business, and the ability to forecast them accurately and efficiently can provide decisive advantages. Darts is an open-source Python library, which provides a wide variety of forecasting models and tools under a single and user-friendly API. It puts emphasis on reducing the experiment cycle duration and improving the ease of using, comparing, and combining different models; from ARIMA to deep learning models.

This talk will give a tour of Darts and some of its main features, such as quick creation and comparison of forecasting models, backtesting, ML-based models applied to time series forecasting, training forecasting models on multiple time series, producing probabilistic forecasts, and integrating external data. We will go over a few toy examples, and see how to address them in a few lines of code.

More resources about Darts here: https://bit.ly/33Y2zNL

Goals of the talk:

Introduce how one can tackle forecasting problems
Obtain great results quickly in a few lines of codes
Pre-requisites:

Basic knowledge of Python
Basic knowledge of data science & machine learning
Key take-aways:

Quickly create forecasts with your own data
Compare and select the best models for your tasks
Potentially integrate additional data such as weather forecasts, GDP, … into your forecasts to improve them

Julien Herzen’s Bio
Julien is the Lead Data Scientist at Unit8, a Swiss Data Science company. His technical specialties are Machine Learning, algorithms and computational techniques. He is a core developer (and creator) of Darts (https://github.com/unit8co/darts), a time series library, and VeGANs (https://github.com/unit8co/vegans), a generative modelling library. Julien has a PhD in Computer Science from EPFL in Lausanne.
GitHub: https://github.com/hrzn/
Twitter: https://twitter.com/jlhrzn/
LinkedIn: https://www.linkedin.com/in/herzen/
Website: https://hrzn.ch//

Francesco Lässig’s Bio
Francesco is a Data Scientist at Unit8 with experience in ML/AI projects in various industries, such as finance, pharma and energy. During his time at Unit8 he has also had the opportunity to become one of the main contributors to the Darts open-source library.
GitHub: https://github.com/pennfranc/
LinkedIn: https://www.linkedin.com/in/francesco…

More resources about Darts here: https://bit.ly/33Y2zNL

 










    close

    This page is only available in english