Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bączek, Jan, Zhylko, Dmytro, Titericz, Gilberto, Darabi, Sajad, Puget, Jean-Francois, Putterman, Izzy, Majchrowski, Dawid, Gupta, Anmol, Kranen, Kyle, Morkisz, Pawel
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2312.17100
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917560978505728
author Bączek, Jan
Zhylko, Dmytro
Titericz, Gilberto
Darabi, Sajad
Puget, Jean-Francois
Putterman, Izzy
Majchrowski, Dawid
Gupta, Anmol
Kranen, Kyle
Morkisz, Pawel
author_facet Bączek, Jan
Zhylko, Dmytro
Titericz, Gilberto
Darabi, Sajad
Puget, Jean-Francois
Putterman, Izzy
Majchrowski, Dawid
Gupta, Anmol
Kranen, Kyle
Morkisz, Pawel
contents While machine learning has witnessed significant advancements, the emphasis has largely been on data acquisition and model creation. However, achieving a comprehensive assessment of machine learning solutions in real-world settings necessitates standardization throughout the entire pipeline. This need is particularly acute in time series forecasting, where diverse settings impede meaningful comparisons between various methods. To bridge this gap, we propose a unified benchmarking framework that exposes the crucial modelling and machine learning decisions involved in developing time series forecasting models. This framework fosters seamless integration of models and datasets, aiding both practitioners and researchers in their development efforts. We benchmark recently proposed models within this framework, demonstrating that carefully implemented deep learning models with minimal effort can rival gradient-boosting decision trees requiring extensive feature engineering and expert knowledge.
format Preprint
id arxiv_https___arxiv_org_abs_2312_17100
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle TSPP: A Unified Benchmarking Tool for Time-series Forecasting
Bączek, Jan
Zhylko, Dmytro
Titericz, Gilberto
Darabi, Sajad
Puget, Jean-Francois
Putterman, Izzy
Majchrowski, Dawid
Gupta, Anmol
Kranen, Kyle
Morkisz, Pawel
Machine Learning
While machine learning has witnessed significant advancements, the emphasis has largely been on data acquisition and model creation. However, achieving a comprehensive assessment of machine learning solutions in real-world settings necessitates standardization throughout the entire pipeline. This need is particularly acute in time series forecasting, where diverse settings impede meaningful comparisons between various methods. To bridge this gap, we propose a unified benchmarking framework that exposes the crucial modelling and machine learning decisions involved in developing time series forecasting models. This framework fosters seamless integration of models and datasets, aiding both practitioners and researchers in their development efforts. We benchmark recently proposed models within this framework, demonstrating that carefully implemented deep learning models with minimal effort can rival gradient-boosting decision trees requiring extensive feature engineering and expert knowledge.
title TSPP: A Unified Benchmarking Tool for Time-series Forecasting
topic Machine Learning
url https://arxiv.org/abs/2312.17100