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{208189,
        author = {Satish Kumar Metta and Kunjam Nageswara Rao},
        title = {Machine Learning-Based Quality Grading of Cashew Kernels Using Linear Regression and XGBoost},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {4},
        pages = {1090-1093},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=208189},
        abstract = {Commercial cashew grading is commonly based on kernel size, shape, color, and the number of kernels per pound. Manual inspection is useful but can be slow and inconsistent when large batches are handled. This paper presents a data-driven approach for classifying whole cashew kernels into six commercial grades: W180, W210, W240, W320, W450, and W500. The study uses a labelled dataset of 6,000 kernel records with geometric, mass, and color attributes. Linear regression is used as a simple baseline, while an Extreme Gradient Boosting (XGBoost) classifier is trained using eleven raw and derived features. The workflow includes feature engineering, stratified train-test splitting, cross-validation, and a web interface for entering measured kernel values. In the project evaluation, the XGBoost classifier achieved 99.58% accuracy on the held-out test set and 99.40% mean cross-validation accuracy. The result suggests that supervised learning can support repeatable preliminary grading when measurements are collected consistently. The proposed interface is intended as a decision-support tool; it does not replace formal quality inspection or certification.},
        keywords = {cashew kernel, quality grading, XGBoost, linear regression, machine learning, classification},
        month = {September},
        }