Prediction of Daily Sales of Individual Products in a Medium-Sized Brazilian Supermarket Using Recurrent Neural Networks Models

Jociano Perin, Lucas Dias Hiera Sampaio, Marlon Marcon, André Roberto Ortoncelli

2025

Abstract

Accurately predicting daily sales of products in supermarkets is crucial for inventory management, demand forecasting, and optimizing supply chain operations. Many studies focus on predicting the total sales of large stores and supermarkets. This study focuses on forecasting daily sales of individual products across various categories. In the experiments, we used Linear Regression and two types of Recurrent Neural Networks: Long Short-Term Memory and Gated Recurrent Unit. One of the contributions of the work is the database used, which is made available for public access and contains daily sales records (between January 2019 and December 2024) of 250 products in a medium-sized supermarket in Brazil. The results show that the predictors’ performance varies significantly from product to product. For one semester, the average of the best 25% resulted in a Root Mean Squared Error (RMSE) of 1.55 and a Mean Absolute Percentage Error (MAPE) of 17.20, and for the average of all products, the best RMSE was 2.12, and the best MAPE was 43.94. We observed similar performance variations for all analyzed semesters. With the results presented, it is possible to understand the performance of the predictors in ten semesters.

Paper Citation

in Harvard Style

Perin J., Sampaio L., Marcon M. and Ortoncelli A. (2025). Prediction of Daily Sales of Individual Products in a Medium-Sized Brazilian Supermarket Using Recurrent Neural Networks Models. In Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA; ISBN 978-989-758-758-0, SciTePress, pages 739-747. DOI: 10.5220/0013649800003967

in Bibtex Style

@conference{data25,
author={Jociano Perin and Lucas Sampaio and Marlon Marcon and André Ortoncelli},
title={Prediction of Daily Sales of Individual Products in a Medium-Sized Brazilian Supermarket Using Recurrent Neural Networks Models},
booktitle={Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA},
year={2025},
pages={739-747},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013649800003967},
isbn={978-989-758-758-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA
TI - Prediction of Daily Sales of Individual Products in a Medium-Sized Brazilian Supermarket Using Recurrent Neural Networks Models
SN - 978-989-758-758-0
AU - Perin J.
AU - Sampaio L.
AU - Marcon M.
AU - Ortoncelli A.
PY - 2025
SP - 739
EP - 747
DO - 10.5220/0013649800003967
PB - SciTePress