Answers are grounded in this paper and cite their sources.
In agriculture, optimizing harvesting schedules is crucial for maximizing profits while minimizing resource waste. This research introduces a novel forecasting model that forecasts the most profitable months to harvest different crops, to optimize agricultural productivity. Using Machine Learning (ML) techniques, our program takes historical price data, seasonal trends, and market dynamics into account to determine the best harvesting dates. To be more specific, we train and evaluate predictive models using 3 years' worth of agricultural data from Krushi Utpanna Bazar Samiti in Haveli Pune using several machine learning techniques, such as Random Forest (RF), Decision Trees (DT), Linear Regression (LR), and others. After a thorough study using the Mean Squared Error (MSE) and R 2 score, it was determined that the DT model performed the best, with an outstanding R 2 score of 99%. Furthermore, we use Streamlit to create an easy-to-use web application that lets farmers input crop types, years, and desired price estimates to determine the best months to harvest. Our approach gives farmers a data-driven means to make informed decisions that increase revenue and improve the sustainability of agriculture. By developing precision agriculture and decision support systems, we want to enhance agricultural productivity and enable more efficient crop management techniques.
No takes yet. Share an insight, caveat, or question.
Sable et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: