Achieving Predictive Precision: Leveraging LSTM and Pseudo Labeling for Volvo's Discovery Challenge at ECML-PKDD 2024

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Metta, Carlo, Gregnanin, Marco, Papini, Andrea, Galfrè, Silvia Giulia, Fois, Andrea, Morandin, Francesco, Fantozzi, Marco, Parton, Maurizio
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913511943176192
author Metta, Carlo
Gregnanin, Marco
Papini, Andrea
Galfrè, Silvia Giulia
Fois, Andrea
Morandin, Francesco
Fantozzi, Marco
Parton, Maurizio
author_facet Metta, Carlo
Gregnanin, Marco
Papini, Andrea
Galfrè, Silvia Giulia
Fois, Andrea
Morandin, Francesco
Fantozzi, Marco
Parton, Maurizio
contents This paper presents the second-place methodology in the Volvo Discovery Challenge at ECML-PKDD 2024, where we used Long Short-Term Memory networks and pseudo-labeling to predict maintenance needs for a component of Volvo trucks. We processed the training data to mirror the test set structure and applied a base LSTM model to label the test data iteratively. This approach refined our model's predictive capabilities and culminated in a macro-average F1-score of 0.879, demonstrating robust performance in predictive maintenance. This work provides valuable insights for applying machine learning techniques effectively in industrial settings.
format Preprint
id arxiv_https___arxiv_org_abs_2409_13877
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Achieving Predictive Precision: Leveraging LSTM and Pseudo Labeling for Volvo's Discovery Challenge at ECML-PKDD 2024
Metta, Carlo
Gregnanin, Marco
Papini, Andrea
Galfrè, Silvia Giulia
Fois, Andrea
Morandin, Francesco
Fantozzi, Marco
Parton, Maurizio
Machine Learning
This paper presents the second-place methodology in the Volvo Discovery Challenge at ECML-PKDD 2024, where we used Long Short-Term Memory networks and pseudo-labeling to predict maintenance needs for a component of Volvo trucks. We processed the training data to mirror the test set structure and applied a base LSTM model to label the test data iteratively. This approach refined our model's predictive capabilities and culminated in a macro-average F1-score of 0.879, demonstrating robust performance in predictive maintenance. This work provides valuable insights for applying machine learning techniques effectively in industrial settings.
title Achieving Predictive Precision: Leveraging LSTM and Pseudo Labeling for Volvo's Discovery Challenge at ECML-PKDD 2024
topic Machine Learning
url https://arxiv.org/abs/2409.13877