In recent years, the increasing use of Artificial Intelligence (AI) models in various application domains raises concerns about issues of model transparency, accountability, and adherence to ethical standards. Explainable Artificial Intelligence (XAI) becomes a relevant paradigm that helps deal with this issue by ensuring that model decisions become interpretable. This paper aims to introduce a framework that would allow implementing explainability in automated decision-making systems and ensure ethical automation. We introduce a methodology based on the combination of intrinsic interpretability, post-hoc interpretation, and the integration of humans-in-the-loop into the process of explanation. The framework makes use of SHAP (SHapley Additive Explanations) and LIME (Local Interpretable Model-Agnostic Explanations) in order to generate both global and local explanations. Based on our quantitative analysis, we demonstrate that the suggested method ensures 94.2% accuracy and high levels of interpretability, outperforming black-box models.