Enhancing water potability prediction: tuned vs default cat boost models

Arun Balaji S.; Subramoniam M.; Poornapushpakala S.; Barani S.

Author(s)

Arun Balaji S. Faculty of Electrical and Electronics Engineering, Sathyabama Institute of Science and Technology, Chennai, India;College of Engineering and Technology, University of Technology and Applied Sciences, Salalah, Oman

Subramoniam M. Faculty of Electrical and Electronics Engineering, Sathyabama Institute of Science and Technology,Chennai,India

Poornapushpakala S. Faculty of Electrical and Electronics Engineering, Sathyabama Institute of Science and Technology,Chennai,India

Barani S. Faculty of Electrical and Electronics Engineering, Sathyabama Institute of Science and Technology,Chennai,India

Abstract

Water is a very important source for every living being on the earth. In such a scenario, access to clean and hygienic potable water remains a challenge in many parts of the world. Conventional water quality testing methods are expensive, and they need expertise. This challenge limits the scalability to test the water quality in environmental monitoring applications. To meet this challenge, a new attempt has been made by integrating the machine learning methods with chemical parameters to estimate the suitability of water for drinking purposes. The General and Tuned Cat Boost technique has been applied to the dataset, which contains the various physicochemical indicators. Various statistical parameters, such as accuracy, precision, recall, and F1-score, but also interpret their behaviour via confusion matrices, ROC curves, precision-recall plots, residual graphs, and feature importance scores, were evaluated for both models. On analysing these parameters, it was observed that the tuned model showed only marginal improvement over the general Cat Boost model. This paper concludes the observations of this study in a comprehensive framework that integrates performance, explainability, and model effectiveness for AI-empowered environmental intelligence systems.

Publication Details

Page(s) 1792-1800

DOI DOI not available

Published Journal: ARPN Journal of Engineering and Applied Sciences, Volume: 20, Issue: 20, Year: 2025

Request the full text from PASTIC

Keywords

cat boost models, tuned cat boost model, SMOTE

References

Akilandeswari A.,Bura V.,Sadagopan P.,Tirumalaikumari P. .2023 .Comparative Analysis of XGBoost and Random Forest for Predicting Water Potability. in Proc. 2023 2nd Int. Conf. Automation, Computing and Renewable Systems (ICACRS), 10405315 : .

Johan J.,Orlanda J.,Pangestu W. S.,Meiliana M.,Achmad S. .2023 .Application of Data Mining Techniques and Hyperparameter Tuning for Accurate Water Potability Classification. in Proc. 2023 10th International Conference on Advanced Informatics: Concept, Theory and Application (ICAICTA), 10390049 : .

Pandya J. K.,Khandelwal S. S.,Tipu K.,Pandya S. .2025 .Advancing Water Quality Management: An Integrated Approach Using Ensemble Machine Learning and Real-Time Interactive Visualization. IEEE Access, 3573589 : 92406-92428.

Alipio M. .2020 .Data-driven IoT-based Water Quality Monitoring and Potability Classification System in Rural Areas. in Proc. 2020 International Conference on Information and Communication Technology Convergence (ICTC), 10 : .

Haq M. I. K.,Ramadhan F. D.,Az-Zahra F.,Kurniawati L.,Helen A. .2021 .Classification of Water Potability Using Machine Learning Algorithms. In Proc. 2021 International Conference on Artificial Intelligence and Big Data Analytics (ICAIBDA), 9689727 : 1-5.

Patel M. S.,Gupta A.,Kumar P. .2024 .A Detailed Analysis of Machine Learning Models to Predict Water Potability. in Proc. 2024 IEEE International Conference on Electronics, Communications and Information (ICEI), 10917239 : 631-639.

P. .2024 .ARIMA Modeling for Reliable Potable Water Identification and Quality Prediction. In Proc. 2024 5th International Conference on Smart Electronics and Communication (ICOSEC), 10722505 : .

P. .2025 .Ensuring Clean Water through Machine Learning Driven Water Quality Prediction. in Proc. 2025 IEEE International Conference on ICICCS, doi: 10.1109/ICICCS65191, 10985149 : .

Alnaqeb R.,Alrashdi F.,Alketbi K.,Ismail H. .2022 .Machine Learning-based Water Potability Prediction. Abu Dhabi, 10017579 : .

K. M. Nasution M. .2025 .Optimization of KNN, SVM, and SVM Kernel in Water Potability Prediction with Hyperparameter Approach. in Proc. 2025 International Conference on Computer Sciences, Engineering, and Technology Innovation (ICoCSETI), 11019055 : .

Manoj R.,Abhishek S.,Nair B. Prathap,A. T. B. Prathap,Ramlal N. Prabhu .2023 .A Contemporary Method of Assessing Water Quality based on the Fusion of Predictive Analytics and Deep Structured Learning. in Proc. 2023 8th International Conference on Communication and Electronics Systems (ICCES), 10192729 : 961-967.

R. .2023 .A Contemporary Method of Assessing Water Quality based on the Fusion of Predictive Analytics and Deep Structured Learning. in Proc. 2023 8th International Conference on Communication and Electronics Systems (ICCES), 10192729 : 961-967.

Biju S. K.,Badgujar C.,Poulose A.,Thomas A. .2024 .Hybrid Horizons: Advancing Water Potability Prediction through Hybrid Machine Learning. in Proc. 2024 IEEE Int. Conf. on Ubiquitous and Future Networks (ICUFN), 10625242 : .

Mishra V.,Upadhyay S.,Jhaba P.,Prajapati S.,Gola K. K. .2023 .An Examination of Guaranteeing the Safety of Drinking Water using Machine Learning. in Proc. 2023 IEEE International Conference on SelfSustainable Artificial Intelligence Systems (ICSSAS), 10331671 : .

Sreekumar V.,Ihsan F.,Reghuram S.,Sarath S. .2024 .A Detailed Analysis of Machine Learning Models to Predict Water Potability. in Proc. 2024 15th International Conference on Computing, Communication and Networking Technologies (ICCCNT), 10725826 : .

Prokhorenkova L,Gusev G,Vorobev A. .2018 .Cat Boost: unbiased boosting with categorical features. Advances in neural information processing systems, 31 : .