Neural Horizons: The Uncharted Future of Deep Learning
Articles

Assessing the Efficacy of Gradient Boosting, Random Forest and ANN Models in Water Demand Prediction

PDF
  • Abhijit Paul,
  • Khushi Bhalla
Abhijit Paul
Department of Computer Science, Swami Vivekananda University, Barrackpore, India
Khushi Bhalla
Department of Information Technology, Amity University, Kolkata, India

Published 2026-05-27

Keywords

  • Water Demand Prediction,
  • Gradient Boosting,
  • Random Forest,
  • Artificial Neural Networks (ANN),
  • Machine Learning

How to Cite

Paul, Abhijit, and Khushi Bhalla. “Assessing the Efficacy of Gradient Boosting, Random Forest and ANN Models in Water Demand Prediction”. Swami Vivekananda University Press, May 2026, pp. 7-16, https://swamivivekanandauniversitypress.com/index.php/svup/article/view/553.

Copyright (c) 2026 Swami Vivekananda University Press

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Abstract

This study evaluates the efficacy of three machine learning algorithms—Random Forest, Gradient Boosting, and Artificial Neural Networks (ANN) in predicting water demand for a city. The performance of these models is compared using statistical metrics including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Square Error (RMSE), and R-squared (R2) on a simulated dataset. The results indicate that the ANN model delivers the most accurate predictions, achieving a prediction accuracy of up to 94%. These findings highlight the potential of ANN in effectively forecasting water demand, providing valuable insights for resource management and planning.

DOI - https://doi.org/10.65525/SVUP.9788199778009.2026.7-16

PDF