Predictive Modeling of Paddy Crop Yields in Jhapa, Nepal: A Machine Learning Approach for Smallholder Agricultural Households.

Agriculture remains the bedrock of Nepal’s economy, yet farmers in the Terai region face increasing yield uncertainty due to erratic climate patterns. This study investigates the efficacy of machine learning (ML) in predicting paddy yields in the Jhapa district. By synthesizing primary survey data from 30 farmers with secondary meteorological data (2019–2023), I developed and compared Linear Regression and Decision Tree models. The results indicate that irrigation access and rainfall distribution are the primary predictors of productivity. The study demonstrates that low-cost AI tools can bridge the data gap in rural Nepal, providing a scalable framework for agricultural decision-support systems. This record includes an anonymized CSV dataset of 30 farmers to ensure research transparency while protecting participant privacy.