Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 325.36 KB
Add to list
  1. Search results
  2. Optimizing sustainability : benchmark...

Optimizing sustainability : benchmarking time-series forecasting models on purchasing data to reduce overproduction

Camilla Carpinelli, Seppe vanden Broucke (UGent) , Bart Baesens, Anna Sigridur Islind and María Óskarsdóttir
(2024) Proceedings of the XXI Conference of the Italian Chapter of AIS - Growing in a digital and sustainable society (ITAIS 2024).
Author
Organization
Abstract
. This study delves into computational sustainability, leveraging AI methods to address sustainable consumption and production challenges. Utilizing historical purchasing data from a prominent Icelandic supermarket chain spanning from 2018 to 2023, the study explores various dimensions of data aggregation, including macro-categories, microcategories, and product labels. Six distinct forecasting methodologies are employed: regression-based, LLM, foundation models, and statistical approaches. Evaluating these models using Root-Mean-SquaredError reveals different findings dependent on dataset aggregation. As a result, datasets with finer aggregation exhibit higher predictive accuracy, with the LLM model consistently outperforming others across macro and micro-category datasets. While one of the foundation models demonstrates comparable performances, LLM’s efficiency is notable despite GPU utilization and longer processing times. The regressor emerges as the most effective predictor for datasets categorized by product labels, with LLM and one foundation model also displaying commendable performance. These findings offer valuable insights for reducing overproduction and optimizing production planning in the production industry, underscoring the importance of leveraging advanced forecasting models to promote sustainability. Further details and implications are discussed in the paper.
Keywords
Forecasting, Data Science, Machine Learning, Benchmark, Sustainability

Downloads

  • Download
    BenchMarking Time Series to Avoid Overproduction.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 325.36 KB

Citation

Please use this url to cite or link to this publication:

MLA
Carpinelli, Camilla, et al. “Optimizing Sustainability : Benchmarking Time-Series Forecasting Models on Purchasing Data to Reduce Overproduction.” Proceedings of the XXI Conference of the Italian Chapter of AIS - Growing in a Digital and Sustainable Society (ITAIS 2024), 2024.
APA
Carpinelli, C., vanden Broucke, S., Baesens, B., Sigridur Islind, A., & Óskarsdóttir, M. (2024). Optimizing sustainability : benchmarking time-series forecasting models on purchasing data to reduce overproduction. Proceedings of the XXI Conference of the Italian Chapter of AIS - Growing in a Digital and Sustainable Society (ITAIS 2024). Presented at the XXI Conference of the Italian Chapter of AIS - Growing in a digital and sustainable society (ITAIS 2024), Piacenza, Italy.
Chicago author-date
Carpinelli, Camilla, Seppe vanden Broucke, Bart Baesens, Anna Sigridur Islind, and María Óskarsdóttir. 2024. “Optimizing Sustainability : Benchmarking Time-Series Forecasting Models on Purchasing Data to Reduce Overproduction.” In Proceedings of the XXI Conference of the Italian Chapter of AIS - Growing in a Digital and Sustainable Society (ITAIS 2024).
Chicago author-date (all authors)
Carpinelli, Camilla, Seppe vanden Broucke, Bart Baesens, Anna Sigridur Islind, and María Óskarsdóttir. 2024. “Optimizing Sustainability : Benchmarking Time-Series Forecasting Models on Purchasing Data to Reduce Overproduction.” In Proceedings of the XXI Conference of the Italian Chapter of AIS - Growing in a Digital and Sustainable Society (ITAIS 2024).
Vancouver
1.
Carpinelli C, vanden Broucke S, Baesens B, Sigridur Islind A, Óskarsdóttir M. Optimizing sustainability : benchmarking time-series forecasting models on purchasing data to reduce overproduction. In: Proceedings of the XXI Conference of the Italian Chapter of AIS - Growing in a digital and sustainable society (ITAIS 2024). 2024.
IEEE
[1]
C. Carpinelli, S. vanden Broucke, B. Baesens, A. Sigridur Islind, and M. Óskarsdóttir, “Optimizing sustainability : benchmarking time-series forecasting models on purchasing data to reduce overproduction,” in Proceedings of the XXI Conference of the Italian Chapter of AIS - Growing in a digital and sustainable society (ITAIS 2024), Piacenza, Italy, 2024.
@inproceedings{01JY12M6MGCWK0JYTV6X4TZPCT,
  abstract     = {{. This study delves into computational sustainability, leveraging AI methods to address sustainable consumption and production challenges. Utilizing historical purchasing data from a prominent Icelandic
supermarket chain spanning from 2018 to 2023, the study explores various dimensions of data aggregation, including macro-categories, microcategories, and product labels. Six distinct forecasting methodologies
are employed: regression-based, LLM, foundation models, and statistical approaches. Evaluating these models using Root-Mean-SquaredError reveals different findings dependent on dataset aggregation. As
a result, datasets with finer aggregation exhibit higher predictive accuracy, with the LLM model consistently outperforming others across
macro and micro-category datasets. While one of the foundation models
demonstrates comparable performances, LLM’s efficiency is notable despite GPU utilization and longer processing times. The regressor emerges
as the most effective predictor for datasets categorized by product labels, with LLM and one foundation model also displaying commendable
performance. These findings offer valuable insights for reducing overproduction and optimizing production planning in the production industry,
underscoring the importance of leveraging advanced forecasting models
to promote sustainability. Further details and implications are discussed
in the paper.}},
  author       = {{Carpinelli, Camilla and vanden Broucke, Seppe and Baesens, Bart and Sigridur Islind, Anna and Óskarsdóttir, María}},
  booktitle    = {{Proceedings of the XXI Conference of the Italian Chapter of AIS - Growing in a digital and sustainable society (ITAIS 2024)}},
  keywords     = {{Forecasting,Data Science,Machine Learning,Benchmark,Sustainability}},
  language     = {{eng}},
  location     = {{Piacenza, Italy}},
  pages        = {{20}},
  title        = {{Optimizing sustainability : benchmarking time-series forecasting models on purchasing data to reduce overproduction}},
  year         = {{2024}},
}