Agrimitra - Smart Crop Recommendation System

Abstract

Agriculture is an essential sector that significantly influences the economy and the livelihood of millions of farmers. However, modern farming is affected by several challenges such as unpredictable weather conditions, fluctuating market prices, improper crop selection, and lack of effective advisory systems. These issues often lead to reduced productivity and financial instability for farmers. To address these challenges, this paper presents AgriMitra, a smart crop recommendation system that supports farmers in making informed and profitable decisions. The system gathers data from multiple sources including real-time weather information, soil characteristics, historical crop data, farmer inputs, and market trends obtained from platforms such as Agmarknet and weather APIs. The collected data is processed and refined to ensure consistency and reliability for further analysis. Machine learning techniques such as Random Forest and XGBoost are applied to recommend crops based on environmental conditions and farmer requirements. These models consider various factors including soil suitability, climate conditions, available budget, and expected market demand. In addition, time-series forecasting models such as ARIMA and Prophet are used to estimate future crop prices and demand patterns, enabling farmers to plan their cultivation strategies more effectively. The system also includes a cultivation plan generator that provides step-by-step guidance for different farming activities such as sowing, irrigation, fertilization, and harvesting. This ensures continuous support throughout the entire farming cycle. Moreover, a multilingual chatbot with both text and voice interaction is integrated into the system to assist farmers, answer their queries, and improve accessibility. An interactive dashboard is designed to present important insights such as crop recommendations, profitability analysis, risk evaluation, and market trends. The system also provides alerts and notifications to help farmers respond to potential risks related to weather conditions, pest attacks, and price fluctuations. By combining Artificial Intelligence, Machine Learning, and real-time data analysis, AgriMitra helps bridge the gap between traditional farming practices and modern technology. The system promotes efficient resource utilization, supports sustainable agriculture, improves crop productivity, and enhances farmer income through better planning and decision-making.

Introduction

Agriculture is a major part of the economy and supports the livelihood of millions of farmers, but farmers often face difficulties in making profitable and data-driven decisions due to unpredictable weather, fluctuating market prices, and lack of integrated advisory systems. Most traditional farming decisions are based on experience rather than analytical insights, which can lead to low productivity and financial loss.

To address these issues, the proposed system AgriMitra – Smart Crop Recommendation System uses Artificial Intelligence and Machine Learning to help farmers make better decisions. It integrates environmental data (soil, weather), economic data (market prices, demand trends), and farmer-specific inputs to recommend the most suitable and profitable crops.

The system includes multiple components: a crop recommendation module using ML models like Random Forest and XGBoost, a price forecasting module using time-series models such as ARIMA and Prophet, and a cultivation planner that provides step-by-step farming guidance. It also features a chatbot and web-based interface for easy access, including multilingual support for farmers.

Existing agricultural tools often fail because they treat soil, weather, and market data separately, lack predictive capabilities, and do not provide personalized or multilingual support. AgriMitra addresses these gaps by combining all these factors into a unified decision-support platform.

In summary, AgriMitra is designed to improve farming decisions by predicting suitable crops, forecasting market prices, and offering actionable cultivation guidance, ultimately aiming to increase productivity, reduce risk, and improve farmer income.

Conclusion

This paper presented AgriMitra – Smart Crop Recommendation System, a solution designed to help farmers make better agricultural decisions based on data analysis and predictive techniques. The system combines information such as soil parameters, weather conditions, market trends, and farmer inputs to generate useful crop recommendations. Machine learning models such as Random Forest and XGBoost are used to identify suitable crops based on environmental conditions. In addition, time-series forecasting models like ARIMA and Prophet are applied to estimate future market prices. This combined approach helps farmers select crops that are both suitable for their land and beneficial in terms of profit. The system also includes a cultivation plan generator and an interactive dashboard, providing support throughout the farming cycle from crop selection to harvesting. A chatbot interface further improves accessibility by allowing farmers to interact with the system in a simple way. The results and system outputs indicate that AgriMitra helps improve decision-making, reduces risks in crop selection, and increases overall productivity. It supports the transition from traditional farming practices to a more data-based approach by providing useful insights and recommendations. Overall, AgriMitra offers a practical and scalable solution for modern agriculture, contributing to better resource utilization, sustainable farming practices, and improved farmer income.

References

[1] A. Laiko, et al., “Crop Recommendation System Using Machine Learning,” International Journal of Agricultural Technology, 2021. [2] R. Singh, et al., “Data-Driven Crop Prediction Using Machine Learning Techniques,” International Journal of Computer Applications, 2020. [3] Government of India, “Agmarknet: Agricultural Marketing Information Network,” [Online]. Available: https://agmarknet.gov.in [4] Government of India, “Kisan Suvidha Mobile Application,” Ministry of Agriculture and Farmers Welfare, India. [5] L. Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. [6] T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” Proceedings of the 22nd ACM SIGKDD, 2016. [7] G. E. P. Box, G. M. Jenkins, and G. C. Reinsel, “Time Series Analysis: Forecasting and Control,” Wiley, 2015. [8] S. J. Taylor and B. Letham, “Forecasting at Scale,” The American Statistician, 2018. [9] P. Patil, et al., “IoT-Based Smart Agriculture System for Efficient Farming,” IEEE Access, 2022. [10] A. Kumar, et al., “Intelligent Smart Farming Using Machine Learning and IoT,” Sensors, 2023.

Copyright

Copyright © 2026 Shivali Pandhare, Prarthana Khairnar, Rushikesh Patil, Vedant Kokare, Bhavana Julme. 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.