Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195963,
        author = {Dr. MK Jayanthi Kannan and Bhavesh Saini and Vivshwan Kr Tomar and Ajay Kumar and Ritik Kumar and Advait Sahu and Malay N Maru},
        title = {Agri-Predict: An AI-Driven Framework for Intelligent Crop Price Forecasting Using Machine Learning and Time-Series Analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {2036-2048},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195963},
        abstract = {Agri-Predict presents a novel hybrid deep learning framework for crop price prediction, designed to address the critical need for accurate forecasting to stabilize agricultural markets and ensure farmer financial security. The proposed system leverages a multi-model approach that integrates three complementary predictive architectures: a Long Short-Term Memory (LSTM) network for capturing complex temporal dependencies and long-term price trends from historical time-series data, an XGBoost regressor for effectively modeling non-linear relationships and handling heterogeneous feature interactions from diverse input variables such as weather patterns, soil conditions, and macroeconomic indicators, and a hybrid LSTM and XGBoost model that synergistically combines the sequential learning capabilities of LSTM with the robust gradient-boosting power of XGBoost. This hybrid architecture enables the system to extract deep temporal features through LSTM layers before passing them to XGBoost for refined final prediction, achieving superior forecasting accuracy over individual models. Extensive evaluation demonstrates that the hybrid LSTM and XGBoost approach significantly outperforms standalone LSTM, XGBoost, and traditional baselines like ARIMA, delivering substantial reductions in error metrics such as RMSE and MAPE. By translating complex, multidimensional data into actionable price intelligence through an accessible interface, Agri-Predict serves as a comprehensive decision-support tool for farmers, policymakers, and supply chain stakeholders, helping reduce price volatility, minimize post-harvest losses, and enhance profitability in the agricultural sector.},
        keywords = {Crop Price Prediction, Long Short-Term Memory (LSTM), XGBoost, Hybrid Deep Learning, Time Series Forecasting, Agricultural Informatics.},
        month = {April},
        }