Machine learning advances for time series forecasting

Достижения машинного обучения в прогнозировании временных рядов
Marcelo Cunha Medeiros, Ricardo Masini, Eduardo F. Mendes
2021-07-01

deep neural networkshigh-frequency financial datapenalized regressionsupervised machine learningtime-series forecasting
Abstract In this paper, we survey the most recent advances in supervised machine learning (ML) and high‐dimensional models for time‐series forecasting. We consider both linear and nonlinear alternatives. Among the linear methods, we pay special attention to penalized regressions and ensemble of models. The nonlinear methods considered in the paper include shallow and deep neural networks, in their feedforward and recurrent versions, and tree‐based methods, such as random forests and boosted trees. We also consider ensemble and hybrid models by combining ingredients from different alternatives. Tests for superior predictive ability are briefly reviewed. Finally, we discuss application of ML in economics and finance and provide an illustration with high‐frequency financial data.
1
It reviews tests for superior predictive ability and illustrates machine-learning applications in economics and finance using high-frequency financial data.
2
Linear methods emphasized include penalized regressions and model ensembles for forecasting.
3
Nonlinear methods reviewed include shallow and deep feedforward or recurrent neural networks, random forests, and boosted trees.
4
The paper surveys recent supervised machine-learning and high-dimensional approaches for time-series forecasting, covering linear and nonlinear methods.
5
The survey examines ensemble and hybrid forecasting models that combine components from different methodological families.

Time series forecasting models, including linear and nonlinear supervised machine-learning and high-dimensional models

Recent advances and predictive performance of penalized regressions, model ensembles, neural networks, tree-based methods, and hybrid models for time-series forecasting

Publication Details
Publication Date
2021-07-01
Journal
Publisher
ISSN
Cited by
721
Access Type
Author Information
Authors
Marcelo Cunha Medeiros
Ricardo Masini
Eduardo F. Mendes
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%