Metaheuristic Optimisation for Marigold Price Forecasting in South India: 26202
Price: ₹ 1000
https://doi.org/10.35716/IJED-26202
Author: Harishbabu P., Nirmala Devi M., Radha M., Angles S. and Jeyalakshmi P.
Author Address: Dr. Nirmala Devi M., Assistant Professor, Department of Physical Sciences and Information Technology Agricultural Engineering College and Research Institute,Tamil Nadu Agricultural University, Coimbatore – 641003 (Tamil Nadu)
Abstract
Flower
price prediction is crucial for the stability of farmers' incomes and market
efficiency. The Stochastic, Machine Learning, and Deep Learning models were
compared and used to predict marigold prices. The Auto Regressive Integrated Moving Average (ARIMA) Models
had the highest prediction errors, whereas the Support Vector Regression (SVR),
Random Forest (RF), and Extreme Gradient
Boosting (XGB) Models had moderate accuracy. Deep Learning Models
outperformed the others due to their ability to capture non-linear and temporal
price patterns. The integration of Grey Wolf Optimisation (GWO) further
improved accuracy, with the optimised Long Short-Term Memory (LSTM) achieving
the lowest prediction errors. Implementation of these models enables farmers
and policymakers to make data-driven decisions, mitigate market risks, and
enhance the efficiency of the value chain.
Keywords
Deep
learning, Grey Wolf Optimisation, machine learning, price prediction.
JEL
Codes
C51,
C52, C53, P42.