Crop Advisor: Intelligent Crop Recommendation System
Viraj Nalawade1, Bhagyashree Kadam2, Chetan Jadhav3, Gaurav Pable4, Pradeep Kokane5
1Viraj Nalawade, Department of Information Technology, JSPM’s BSIOTR Wagholi, Pune (Maharashtra), India.
2Bhagyashree Kadam, Department of Computer Science Engineering, Savitribai Phule Pune University, Pune (Maharashtra), India.
3Chetan Jadhav, Department of Information Technology, JSPM’s BSIOTR Wagholi, Pune (Maharashtra), India.
4Gaurav Pabale, Department of Information Technology, JSPM’s BSIOTR Wagholi, Pune (Maharashtra), India.
5Pradeep Kokane, Department of Information Technology, JSPM’s BSIOTR Wagholi, Pune (Maharashtra), India.
Manuscript received on 06 January 2025 | First Revised Manuscript received on 17 January 2025 | Second Revised Manuscript received on 16 April 2025 | Manuscript Accepted on 15 May 2025 | Manuscript published on 30 May 2025 | PP: 1-6 | Volume-5 Issue-1 May 2025 | Retrieval Number: 100.1/ijae.A152505010525 | DOI: 10.54105/ijae.A1525.05010525
Open Access | Ethics and Policies | Cite | Zenodo | OJS | Indexing and Abstracting
© The Authors. Published by Lattice Science Publication (LSP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Agriculture has long been a cornerstone of the Indian economy, crucial in sustaining livelihoods and contributing to national growth. By 2024, the sector will contribute approximately 18-20% of India’s GDP and employ nearly half of the population. It also ensures food security for over 1.4 billion people. However, crop yields per hectare continue to lag international standards, which has been a significant factor contributing to the rising suicide rates among farmers. This paper proposes a machine learning-based Crop Regulating System to assist farmers. The system takes inputs such as historical and current yield data, weather conditions, soil quality and fertiliser usage from farmers and predicts weather impact, rainfall, and disease effect to predict crop yield before sowing. Also, the system takes inputs such as current market data, sowed land, market import/export data, historical retail data, and consumer data for market demand analysis. Machine learning algorithms analyze this data to predict the market demand and the yield for a chosen crop. After that machine learning algorithms like Regression Forest (RF) and Support Vector Machine (SVM) were used to provide Decision support to Farmers. Regression models like Support Vector Machines (SVM) and Random Forests (RF), Multiple Linear Regression (MLR) and classification models like K-Nearest Neighbors (KNN) are utilized for Crop Yield Prediction. Time series models such as AutoRegressive Integrated Moving Average (ARIMA), and Genetics Algorithms (GAs) are used for Market Demand Analysis.
Keywords: Crop Yield Prediction, Market Demand Analysis, Machine Learning, Random Forest, Support Vector Machine (SVM), Multiple Linear Regression (MLR), K-Nearest Neighbors (KNN), AutoRegressive Integrated Moving Average, Time Series Models, Genetics Algorithms (GAs), Classification Models.
Scope of the Article: Agricultural Biotechnology