FarmaSuit: The Agricultural Recommendation System

Abstract

Agriculture remains a key sector of the Indian economy and continues to support a large share of the population for livelihood. However, unpredictable variations in weather and environmental conditions significantly affect crop productivity and yield. Machine Learning (ML) has emerged as an effective decision-support approach for Crop Yield Prediction (CYP), helping improve decisions related to crop selection and cultivation planning based on soil and climatic parameters.Several ML and AI-based techniques have been applied for crop yield estimation, crop classification, and fertilizer recommendation using input variables such as soil nutrients, pH value, temperature, humidity, and rainfall. While Neural Networks show promising results, they often face limitations such as reduced prediction efficiency and difficulty in minimizing prediction error. Similarly, many supervised learning methods struggle to model complex nonlinear relationships between input and output variables. Comparative observations across commonly used techniques highlight the need for more accurate and reliable predictive models to improve agricultural decision-making and sustainable productivity.

Introduction

Agriculture is a key pillar of India’s economy, but farmers face persistent challenges such as unsuitable crop selection, inefficient fertilizer use, and unpredictable weather, all of which reduce productivity and income. To address these issues, FarmaSuit is proposed as a web-based, machine learning–driven agricultural recommendation system that supports data-driven and sustainable farming decisions.

FarmaSuit recommends suitable crops and fertilizers based on soil parameters (N, P, K, pH) and environmental factors such as temperature, humidity, and rainfall. It also integrates weather-based insights to assist farmers in planning irrigation, sowing, and harvesting. The platform combines agricultural domain knowledge with AI and analytics, and is designed to be user-friendly and accessible for farmers in rural and semi-urban areas.

The system employs multiple machine learning algorithms, including SVM, KNN, Random Forest, Gradient Boosting, and Neural Networks, to improve prediction accuracy and resource efficiency. Related studies show that ML techniques achieve high accuracy in crop recommendation and fertilizer prediction, though challenges remain in model stability and reliability, especially for fertilizer optimization.

The proposed architecture involves data collection, preprocessing, feature extraction, and model training/testing using various ML and deep learning techniques. In operation, FarmaSuit collects user inputs, cleans and processes the data, applies trained models, and finally delivers crop and fertilizer recommendations through a web interface. Overall, FarmaSuit aims to enhance crop yield, optimize resource use, and promote eco-friendly and sustainable agricultural practices.

Conclusion

The FarmaSuit project successfully shows how machine learning and data analytics can improve traditional farming by enabling more accurate and data-driven decision-making. By analyzing key soil parameters such as N, P, K values and pH along with important weather conditions, the system provides reliable crop and fertilizer recommendations that support better productivity and sustainable farming practices. Its user-friendly interface and well-structured design make it easy for users to interact with the platform, while the use of models such as SVM, KNN, Random Forest, Gradient Boosting, and Neural Networks helps generate intelligent insights for improved yield and reduced resource wastage. Overall, FarmaSuit effectively bridges the gap between agricultural needs and modern technology, proving that smart, data-based recommendations can make farming more efficient, sustainable, and future-ready.

References

[1] D. Javanarayana Reddy and M. Rudra Kumar,“Crop Yield Prediction using Machine Learning Algorithm,” in Proceedings of the Fifth International Conference on Intelligent Computing and Control Systems (ICICCS 2021), pp. 1466–1472 IEEE, 2021 [2] E. Elbasi, C. Zaki, A. E. Topcu, W. Abdelbaki, A. I. Zreikat, E. Cina, A. Shdefat, and L. Saker,“Crop Prediction Model Using Machine Learning Algorithms,” Applied Sciences, vol. 13, p. 9288, 2023 [3] 3.P. Jain and A. Mehta, \"Data-Driven Decision Support for Smart Farming using Soil and Weather Analytics,\" IEEE Access, vol. 11, pp. 54710-54722, 2023 [4] 4.T. S. T. Tanaka, G. B. M. Heuvelink, T. Mieno, and D. S. Bullock,“Can machine learning models provide accurate fertilizer recommendations?” Precision Agriculture, vol. 25, pp. 1839–1856, 2024

Copyright

Copyright © 2026 Atharv Wavare, Prof. Sweta Kale, Madhavi Sonar, Parth Tonde, Dnyaneshwari Salgar. This 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.