Time series forecasting and classification remains an important yet challenging problem for a variety of businesses. Deep learning-based methods have recently shattered time-series research benchmarks yet remain seldom used in the industry. In this seminar, we will discuss how to use deep learning to forecast and classify real world time series datasets. We will walk through the use of several open-source frameworks like PyTorch, Flow Forecast (a new open-source deep learning for time series forecasting library), Kubernetes, and Airflow to train, validate, interpret, and deploy deep time series models at scale. Finally, we will discuss techniques for monitoring existing models in production, re-training models periodically, and checking for distribution drift on changing datasets. Participants will leave with a practical understanding of how to leverage open-source, deep learning packages to solve real world business needs like sales/revenue forecasting, predictive maintenance, demand prediction, and much more.

Local ODSC chapter in Boston, USA

Get your ODSC West 2021 pass with 75% OFF -

Instructor's Bio

Isaac Godfried

Machine Learning Researcher CoronaWhy

Isaac Godfried is a data scientist and AI researcher focused on applying deep learning to real world problems. Isaac has extensive experience forecasting time series data in many different industries such as healthcare (patient vitals, infectious disease spread), retail (store sales, surplus stock), and climate (stream flows, precipitation). Outside of time series Isaac has trained and deployed models for NLP and CV and has a particular interest in models that can leverage textual and image data to improve forecasts.


  • 1

    Deep Learning for Time Series in Industry: The Promise and the Barriers

    • AI+ Training

    • Webinar recording

    • AI+ Subscription Plans