Home / Current Issue / Paper 1711906
Agricultural Market Price Prediction Using Machine Learning and ARIMA Time Series Models: A Review
Subject area: Science,Engineering and Technology · Area of research: Artificial Intelligence and Data Science
DOI: https://doi.org/10.64388/IREV9I5-1711906
Abstract
Agricultural commodity price forecasting is essential for farmers, traders, policy makers and supply-chain managers. Traditional econometric/time-series methods such as ARIMA/SARIMA have been widely used because of simplicity and interpretability, while machine learning (ML) and deep learning (DL) approaches (Random Forest, XGBoost, SVR, LSTM, CNN, hybrid ARIMA?LSTM) are increasingly applied to capture nonlinearities and complex patterns. This review synthesizes recent literature (2018?2025), compares ARIMA and ML approaches, highlights hybrid strategies, discusses datasets and evaluation practices, identifies common challenges (data quality, exogenous factors, explainability), and proposes promising research directions for robust, deployable forecasting systems.
Keywords
Agricultural price forecasting, time series analysis, ARIMA, SARIMA, machine learning, deep learning, LSTM, XGBoost, hybrid models, nonlinear prediction, data quality, feature engineering, explainable AI, agricultural economics, predictive analytics.
How to cite this paper
@article{1711906,
author = {Vedant Joshi, Aadesh Polekar, Yash Pardeshi, Pranay Pawar, Prof. Tushar Kolhe},
title = {Agricultural Market Price Prediction Using Machine Learning and ARIMA Time Series Models: A Review},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {9},
number = {5},
pages = {1047-1054},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1711906.pdf},
abstract = {Agricultural commodity price forecasting is essential for farmers, traders, policy makers and supply-chain managers. Traditional econometric/time-series methods such as ARIMA/SARIMA have been widely used because of simplicity and interpretability, while machine learning (ML) and deep learning (DL) approaches (Random Forest, XGBoost, SVR, LSTM, CNN, hybrid ARIMA?LSTM) are increasingly applied to capture nonlinearities and complex patterns. This review synthesizes recent literature (2018?2025), compares ARIMA and ML approaches, highlights hybrid strategies, discusses datasets and evaluation practices, identifies common challenges (data quality, exogenous factors, explainability), and proposes promising research directions for robust, deployable forecasting systems.},
keywords = {Agricultural price forecasting, time series analysis, ARIMA, SARIMA, machine learning, deep learning, LSTM, XGBoost, hybrid models, nonlinear prediction, data quality, feature engineering, explainable AI, agricultural economics, predictive analytics.},
month = {November},
doi = {https://doi.org/10.64388/IREV9I5-1711906}
}