Breast cancer remains a leading cause of mortality worldwide, especially among women, emphasizing the urgent need for accurate and early detection methods. This study presents an Explainable Artificial Intelligence (XAI) framework for the classification of breast cancer, integrating machine learning and deep learning models to enhance diagnostic precision and interpretability. The proposed system leverages CatBoost for handling structured data, while deep learning models such as LSTM, MLP, and CNN are employed to capture complex, non-linear patterns in the input features. To ensure clinical reliability and transparency, explainability tools are incorporated to highlight the most influential features contributing to classification decisions. Experimental results demonstrate high accuracy across all models, with CatBoost excelling in interpretability and CNN delivering strong performance on imaging-based data. The integration of explainability not only facilitates trust in automated systems but also aids medical professionals in understanding model predictions, thereby contributing to informed decision-making in breast cancer diagnosis and treatment planning.

Keywords: Breast Cancer Classification, Explainable Artificial Intelligence (XAI), CatBoost, LSTM, MLP, CNN, Deep Learning, Feature Importance, Medical Diagnosis, Early Detection.