Integrating Big Data and Machine Learning to Support Smart Village Decisions for Agricultural Productivity Improvement

The purpose of this study develops and analyzes an integrated framework that combines Big Data analytics and Machine Learning (ML) techniques to enhance agricultural productivity within the Smart Village ecosystem. In addition to conducting a bibliometric and systematic review of peer-reviewed literature, the research proposes a conceptual model illustrating how data-driven technologies can strengthen rural decision support systems. The proposed framework is validated conceptually through synthesis of prior empirical findings and structured analysis using Scopus-indexed publications from 2019–2024. Results reveal that the integration of Big Data and ML significantly improves prediction accuracy, enables early pest detection, optimizes irrigation management, and supports sustainable productivity among smallholder farmers. The study contributes to the body of knowledge by offering a comprehensive synthesis of technological applications in rural contexts, while acknowledging limitations related to data availability, infrastructure constraints, and limited adoption among digitally marginalized communities. In conclusion, integrating Big Data and ML provides transformative potential for rural agriculture and smart village initiatives, though success depends on inclusive frameworks, affordable solutions, and supportive policy environments. Future research should focus on developing scalable, context-sensitive ML models, advancing federated learning for data security, and strengthening capacity building to ensure equitable adoption across diverse rural communities.