In the realm of automated resume categorization, the pressing need for both accuracy and interpretability in machine learning models remains a challenge. This research addresses the challenges of accuracy and interpretability in automated resume categorization by integrating K-Nearest Neighbors (KNN) with Local Interpretable Model-agnostic Explanations (LIME). Utilizing a diverse dataset from various industries, the study involves preprocessing resumes with TF-IDF vectorization and training the KNN algorithm with optimized parameters. LIME provides local explanations for individual predictions, enhancing transparency in the decision-making process. The framework is evaluated on standard metrics and demonstrated with real-world resumes, showcasing its effectiveness in practical recruitment scenarios. This approach advances the literature by combining KNN’s simplicity with LIME’s interpretability, promoting trust and fairness in automated recruitment systems.