DeepAI
Log In Sign Up

Fast and frugal time series forecasting

02/23/2021
by   Fotios Petropoulos, et al.
0

Over the years, families of forecasting models, such as the exponential smoothing family and Autoregressive Integrated Moving Average, have expanded to contain multiple possible forms and forecasting profiles. In this paper, we question the need to consider such large families of models. We argue that parsimoniously identifying suitable subsets of models will not decrease the forecasting accuracy nor will it reduce the ability to estimate the forecast uncertainty. We propose a framework that balances forecasting performance versus computational cost, resulting in a set of reduced families of models and empirically demonstrate this trade-offs. We translate computational benefits to monetary cost savings and discuss the implications of our results in the context of large retailers.

READ FULL TEXT

page 1

page 2

page 3

page 4

07/08/2018

Predictive Likelihood for Coherent Forecasting of Count Time Series

A new forecasting method based on the concept of the profile predictive ...
03/16/2018

Forecasting Economics and Financial Time Series: ARIMA vs. LSTM

Forecasting time series data is an important subject in economics, busin...
02/09/2021

The future of forecasting competitions: Design attributes and principles

Forecasting competitions are the equivalent of laboratory experimentatio...
12/03/2012

Nonparametric risk bounds for time-series forecasting

We derive generalization error bounds for traditional time-series foreca...
02/24/2022

Robust Probabilistic Time Series Forecasting

Probabilistic time series forecasting has played critical role in decisi...
12/28/2018

Cardiology Admissions from Catheterization Laboratory: Time Series Forecasting

Emergent and unscheduled cardiology admissions from cardiac catheterizat...