Binary Delivery Time Classification and Vehicle's Reallocation Based on Car Variants. SEAT: A Case Study

Juan Manuel García Sánchez, Xavier Vilasís Cardona, Alexandre Lerma Martín

Research output: Book chapterConference contributionpeer-review

Abstract

This note provides a solution to vehicle's compound allocation problem. It has been treated as a classification task employing different Machine Learning (ML) algorithms. It is performed using the known car attributes and the time that vehicles have spent in the compound region, i.e., inventory warehouse, waiting the customer delivery day. Classification results have been assessed with F1 Score and CatBoost has arisen as the best technique, with values larger than 70%. Finally, reallocation strategy has been tested and outcomes exhibit that company's expert performance is equaled or overcame with respect to time distribution.

Original languageEnglish
Title of host publicationArtificial Intelligence Research and Development - Proceedings of the 24th International Conference of the Catalan Association for Artificial Intelligence
EditorsAtia Cortes, Francisco Grimaldo, Tommaso Flaminio
PublisherIOS Press BV
Pages147-150
Number of pages4
ISBN (Electronic)9781643683263
DOIs
Publication statusPublished - 17 Oct 2022
Event24th International Conference of the Catalan Association for Artificial Intelligence, CCIA 2022 - Sitges, Spain
Duration: 19 Oct 202221 Oct 2022

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume356
ISSN (Print)0922-6389

Conference

Conference24th International Conference of the Catalan Association for Artificial Intelligence, CCIA 2022
Country/TerritorySpain
CitySitges
Period19/10/2221/10/22

Keywords

  • Anticipatory Shipping
  • Automotive OEM
  • Classification
  • Customer Delivery Time Distribution
  • F1 Score
  • Machine Learning
  • Vehicle Reallocation

Fingerprint

Dive into the research topics of 'Binary Delivery Time Classification and Vehicle's Reallocation Based on Car Variants. SEAT: A Case Study'. Together they form a unique fingerprint.

Cite this