Authors: Mariyam Malik, Professor Dr. B Sasi Kumar
Abstract: Artificial Intelligence (AI) is now widely used in decision-making systems developed by technology giants to drive decisions, triggering concerns related to fairness, transparency, and accountability. In response, organizations such as IBM, Microsoft, and Google have published internal AI ethics policies aligned with international standards. Crucially, these policies prove descriptive in nature and lack measurable methods for evaluation. The work envisioned in this paper, purposefully, a quantitative framework to assess the alignment between corporate AI ethics policies and deployed machine learning systems. A supervised learning model is implemented as a case study using a public income prediction dataset containing sensitive demographic attributes. Fairness is evaluated using demographic parity, while model transparency is examined through SHAP-based feature attribution techniques. We apply additional plausible constraints to address privacy and accountability concerns by limiting sensitive identifiers and enforcing a modular, reproducible pipeline. An aggregated Ethics Compliance Score combines multiple ethical dimensions into a single evaluation measure, showing that ethical risks may persist even in accurate models. Unlike prior work that focuses 27 separately on principles or tools, the proposed framework links corporate ethics commitments directly to quantitative system-level indicators, providing a practical basis for internal AI governance.
