Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{180557,
        author = {Philsy v martin and Navya Maria Jomy and Vyshali J Gogi},
        title = {A Holistic Framework for Predicting and Addressing Donor Churn in NGOs: Insights from Machine Learning and Temporal Analytics},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {6335-6340},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=180557},
        abstract = {This research develops a predictive system for donor churn, aimed at identifying and mitigating donor attrition within nonprofit organizations. The system analyzes a large dataset that contains organizational indicators and financial data, including income, expenses, and asset liabilities, by utilizing machine learning techniques. With an emphasis on trends that forecast donor behaviour and churn likelihood based on revenue declines and past donor interaction, the dataset covers several years. The dataset was prepared for model training using data preparation approaches such as feature engineering to generate lagged revenue and churn probability, KNN-based imputation for missing values, and meticulous filtering for consistency. To forecast donor turnover, a number of machine learning algorithms were trained, including as XGBoost, Random Forest, and Logistic Regression. Hyperparameter tuning and cross-validation optimized model performance, while feature importance analysis identified key factors driving churn predictions. The final system offers an interactive, real-time solution that enables nonprofit organizations to monitor donor trends, anticipate churn, and derive actionable insights. By integrating robust data processing with predictive analytics and visualization. This end-to-end solution combines data processing, machine learning, and real-time visualization, enabling organizations to proactively address donor churn and enhance long-term sustainability},
        keywords = {Donor churn, machine learning, predictive analytics, feature engineering, hyperparameter tuning, real-time visualization, nonprofit organizations},
        month = {November},
        }