Bring or buy? Predicting water habits with machine learning
This study applies a Random Forest classification model to analyze individual preferences related to the habit of carrying drinking water during daily routines or travel. Data were collected through a structured questionnaire covering demographic, lifestyle, and perception based features. The model...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | en |
| Published: |
IEEE
2025
|
| Subjects: | |
| Online Access: | https://umpir.ump.edu.my/id/eprint/46178/1/Bring_or_Buy_Predicting_Water_Habits_with_Machine_Learning.pdf https://umpir.ump.edu.my/id/eprint/46178/ https://doi.org/10.1109/ICoAILO66760.2025.11155948 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This study applies a Random Forest classification model to analyze individual preferences related to the habit of carrying drinking water during daily routines or travel. Data were collected through a structured questionnaire covering demographic, lifestyle, and perception based features. The model achieved a cross validated accuracy of 81%, with high F1 scores for both target classes, indicating strong predictive performance. Key influencing factors included perceptions of water cleanliness, the frequency of cleaning reusable bottles, the availability of public refill stations, and lifestyle habits such as physical activity and work setting. The results offer insights into hydration behavior and suggest potential avenues for promoting more sustainable water consumption practices. These findings can inform public health initiatives, environmental campaigns, and product development aimed at supporting the use of reusable water bottles and improving access to clean drinking water. |
|---|