Enriched Multi-Model System to Predict Crop Yield and Price Recommendations through Machine Learning

Authors

  • Priyanka Bhate Department of Computer Engineering, KJ College of Engineering and Management Research, Pune, India
  • Aparna Hambarde Department of Computer Engineering, KJ College of Engineering and Management Research, Pune, India
  • Nikita Kulkarni Department of Computer Engineering, KJ College of Engineering and Management Research, Pune, India

Keywords:

Crop prediction; Crop price estimation; Deep Learning models; Long short-term memory; Linear Regression; Hybrid recommendation.

Abstract

When farmers make poor choices, their crops do not produce enough, and when harvest prices are low, they incur unjustifiable financial losses. In extreme cases, this may lead to the farmer's death or a termination of farming as a profession. Predicting agricultural output, pricing, and other suggestions using artificial intelligence is a scientific approach to prevent this problem. While a lot of studies have tried to forecast crop yields and warn farmers of impending issues, relatively few have offered practical advice on what to do to harvest crops for optimal profit or suggested other crops to plant. As a result, artificial intelligence is the way to go for farmers those want to better their financial situations while also saving lives. In this paper, enriched multi-model system is employed in predicting crop yield and price recommendations through machine learning. The proposed approach combines a deep learning ensemble with a machine learning linear regression model to forecast prices. Agricultural yield forecasting using a neural network with long short-term memory. As a whole, the two models work well together to improve crop yield, price, and suggestion prediction by reducing the root-mean-square error (RMSE).

Downloads

Download data is not yet available.

Published

2024-03-14

How to Cite

Bhate, P. ., Hambarde, A. ., & Kulkarni, N. . (2024). Enriched Multi-Model System to Predict Crop Yield and Price Recommendations through Machine Learning. Journal of Information Systems Research and Practice, 2(1), 13–27. Retrieved from https://mjlis.um.edu.my/index.php/JISRP/article/view/52111