An Introduction to Forecasting Using Orbit
Offered By: Data Science Festival via YouTube
Course Description
Overview
Explore the fundamentals of forecasting using Orbit in this 21-minute conference talk from the Data Science Festival. Delve into the world of probabilistic forecasting techniques based on Bayesian Inference as Murtaza Hussain, a Data Scientist at Connex One, introduces Orbit, a tool developed internally at Uber for long and short-term forecasting. Learn about the three exponential smoothing models implemented in Orbit, its fit-predict paradigm similar to Scikit Learn, and its feature-rich modules for hyperparameter tuning, back testing, and diagnostics. Discover how Connex One utilized Orbit to build a proof of concept for forecasting demand in their client-facing Technical Support team. Gain insights into the practical application of Orbit and see the results obtained from this innovative forecasting tool. This talk, part of the Data Science Festival Sandbox Sessions in 2023, offers valuable knowledge for data scientists and business professionals seeking to minimize costs and ensure service quality through effective forecasting techniques.
Syllabus
An Introduction to Forecasting using Orbit - Data Science Festival
Taught by
Data Science Festival
Related Courses
Supply Chain PlanningRutgers University via Coursera Pronóstico de la generación de energía eólica y solar fotovoltaica
Galileo University via edX Forecasting in R
DataCamp Mining Data from Time Series
Pluralsight Applied Time Series Analysis and Forecasting with R
Pluralsight