For2For: Learning to forecast from forecasts

01/14/2020
by   Shi Zhao, et al.
17

This paper presents a time series forecasting framework which combines standard forecasting methods and a machine learning model. The inputs to the machine learning model are not lagged values or regular time series features, but instead forecasts produced by standard methods. The machine learning model can be either a convolutional neural network model or a recurrent neural network model. The intuition behind this approach is that forecasts of a time series are themselves good features characterizing the series, especially when the modelling purpose is forecasting. It can also be viewed as a weighted ensemble method. Tested on the M4 competition dataset, this approach outperforms all submissions for quarterly series, and is more accurate than all but the winning algorithm for monthly series.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/16/2020

A Strong Baseline for Weekly Time Series Forecasting

Many businesses and industries require accurate forecasts for weekly tim...
research
04/08/2019

Application of data compression techniques to time series forecasting

In this study we show that standard well-known file compression programs...
research
03/10/2022

Forecasting the abnormal events at well drilling with machine learning

We present a data-driven and physics-informed algorithm for drilling acc...
research
06/23/2021

MegazordNet: combining statistical and machine learning standpoints for time series forecasting

Forecasting financial time series is considered to be a difficult task d...
research
08/30/2019

FFORMPP: Feature-based forecast model performance prediction

This paper introduces a novel meta-learning algorithm for time series fo...
research
08/22/2023

Forecasting inflation using disaggregates and machine learning

This paper examines the effectiveness of several forecasting methods for...
research
03/01/2022

Molecular Dynamics of Polymer-lipids in Solution from Supervised Machine Learning

Machine learning techniques including neural networks are popular tools ...

Please sign up or login with your details

Forgot password? Click here to reset