Abstract Details
Activity Number:
|
480
|
Type:
|
Topic Contributed
|
Date/Time:
|
Wednesday, August 12, 2015 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Section on Statistical Computing
|
Abstract #316867
|
|
Title:
|
Automated Forecasting with Big Data
|
Author(s):
|
Sean Taylor* and Alex Peysakhovich
|
Companies:
|
Facebook and Facebook
|
Keywords:
|
forecasting ;
big data ;
machine learning ;
sensors
|
Abstract:
|
We describe the challenges and opportunities of forecasting thousands or even millions of related time series. Our approach is to place the extrapolation problem in a statistical learning framework fit large models which directly minimize empirical risk across many forecast horizons. We show how combining streaming feature generation with scalable regularized regression techniques can produce good forecasts and predictive intervals for extremely large data sets. We call the resulting system "Prophet," and it is currently used at Facebook to almost completely automate forecasting across a wide variety of problems.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2015 program
|
For program information, contact the JSM Registration Department or phone (888) 231-3473.
For Professional Development information, contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
2015 JSM Online Program Home
ASA Meetings Department
732 North Washington Street, Alexandria, VA 22314
(703) 684-1221 • meetings@amstat.org
Copyright © American Statistical Association.