Farmingo: A MERN and ML-Integrated Platform for Smart, Community-Driven Agriculture

Abstract

India’s agricultural sector, while possessing immense potential, faces persistent challenges that have discouraged farmer participation. Limited access to modern resources, inadequate technical knowledge, and unorganized marketplaces have contributed to these issues. A recent NABARD report (2023) reveals that although 58% of farmers are aware of schemes like the Kisan Credit Card, only 28% successfully access them, and over 76% report not receiving the Minimum Support Prices (MSP), often selling their crops at a loss [1]. This study aims to address these challenges through the development of Farmingo, a unified web-based platform designed to empower farmers with intelligent agricultural insights and facilitate community-driven support. Farmingo has been developed using the MERN stack (MongoDB, Express.js, React.js, Node.js) and integrates Pythonbased machine learning (ML) models served via Flask APIs. The system provides real-time predictions and recommendations for crop selection and fertiliser application, based on inputs such as soil characteristics, weather patterns, and crop-specific data. Additionally, the platform offers features that enable users to buy, rent, or list farming equipment, as well as share knowledge through lessons, blogs, and videos. To ensure Farmingo’s practical relevance, the platform’s architecture was designed to seamlessly connect the MERN-based frontend with the ML models, enabling a cohesive and user-friendly experience. Field implementation and user feedback suggest that Farmingo fosters improved decisionmaking and encourages the adoption of data-driven farming practices among farmers. Unlike existing agri-tech solutions that typically focus on specific aspects of farming, Farmingo adopts a holistic approach by integrating intelligent decision support with a collaborative social environment. This integration aims to bridge knowledge gaps and promote equitable access to resources within India’s agricultural ecosystem. The paper elaborates on the system design, implementation of machine learning (ML) algorithms, and real-world use cases encountered during pilot testing. It also outlines future directions for Farmingo, including the incorporation of crop disease detection modules, enhanced visibility of government schemes, and continuous updates to the dataset to improve region-specific agricultural intelligence. The findings of this research highlight the transformative potential of combining technology and community-driven support to bolster India’s agricultural sector.