Scholarlink

This study presents a machine learning approach to predict household connections to public water networks using socio-economic indicators. The proposed CatBoost-based model integrates household characteristics, infrastructure quality, and educational factors to predict water connectivity levels. Our model achieved high predictive accuracy ( \(\text {R}^{2}\) = 85%), with feature importance analysis identifying infrastructure comfort, residence type, and basic amenities as key predictors. The findings demonstrate the model’s effectiveness in identifying areas for water infrastructure development and supporting evidence-based policy decisions. This research contributes to data-driven infrastructure planning by providing a reliable framework for predicting water network connectivity patterns.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine Learning-Based Prediction of Household Water Network Connectivity Using Socio-Economic Indicators

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Youness Boudrik,
  • Rachid Hasnaoui,
  • Achraf Touil

摘要

This study presents a machine learning approach to predict household connections to public water networks using socio-economic indicators. The proposed CatBoost-based model integrates household characteristics, infrastructure quality, and educational factors to predict water connectivity levels. Our model achieved high predictive accuracy ( \(\text {R}^{2}\) = 85%), with feature importance analysis identifying infrastructure comfort, residence type, and basic amenities as key predictors. The findings demonstrate the model’s effectiveness in identifying areas for water infrastructure development and supporting evidence-based policy decisions. This research contributes to data-driven infrastructure planning by providing a reliable framework for predicting water network connectivity patterns.