Darts - Unifying Time Series Forecasting Models from ARIMA to Deep Learning

Explore time series forecasting techniques from traditional ARIMA models to cutting-edge deep learning approaches in this 45-minute conference talk from EuroPython 2021. Discover Darts, an open-source Python library that unifies various forecasting models under a simple API, enabling quick development and comparison of both classical statistical methods and advanced machine learning techniques. Learn best practices for pre-processing, backtesting, and obtaining accurate forecasts efficiently. Gain insights into tackling forecasting problems and see how Darts can streamline your workflow, allowing you to achieve great results with minimal code. Basic knowledge of Python and Pandas, along with intermediate understanding of data science and machine learning concepts, is recommended for optimal comprehension of this informative presentation.

G. Grosch, F. Lässig - Darts: Unifying time series forecasting models from ARIMA to Deep Learning