Learn modern forecasting techniques to help predict future business outcomes

Help optimize business processes by predicting future outcomes using time series forecasting techniques. How? Join other professionals and learn from leading experts Tim Januschowski and Jan Gasthaus in their live online course starting January 17. 

Over the course of 5 two-hour sessions with Tim and Jan, you will:

• Identify whether your business problem can/should be solved as a forecasting problem and discern between different types of forecasting problems.
• Study examples from companies such as Zalando and Amazon.
• Use and tune global ML-powered methods such as Gradient Boosted Trees and Neural Network-based methods like DeepAR.
• Learn best practices to avoid pitfalls in production.

Unlike other online learning platforms like Udemy, Coursera or Linkedin, Sphere allows learners to work with Tim and Jan live — both in sessions and during office hours — to improve their forecasting skills. All while networking with other top-tier practitioners in the industry. 

Since the course is also fully accredited, you can likely expense the course using your L&D budget. We can help with an email template to send to your manager or HR department head (feel free to email leah@getsphere.com).

Tim is the Director of the Pricing Platform at Zalando SE, where he leads the organization responsible for setting prices for the Zalando wholesale business. Before Zalando, Tim led the time series science organisation for Amazon Web Services’ AI division. In addition, he is Director at the International Institute of Forecasters, serves as a reviewer for the major ML venues, lectures at TU Munich, and advises start-ups such as WhyLabs.

Jan Gasthaus is a Principal Machine Learning Scientist at Amazon, where he works on some of the largest time series prediction problems on the planet. As part of AWS AI Labs, he helped create the technology behind AWS services such as Sagemaker, Amazon Forecast, and Amazon DevOps Guru, and co-created the open-source deep learning forecasting library GluonTS. He has co-authored over 30 scientific articles on time series modeling, served as area chair and reviewer for NeurIPS and other major ML conferences, and has given numerous keynotes, lectures, and tutorials on forecasting.