Towards Defining a Trustworthy Artificial Intelligence System Development Maturity Model

The trustworthiness of artificial intelligence (AI) has been challenged for quite some time. The AI results will be trustworthy and reliable if trust-related principles are built into the AI system along with effective AI governance and monitoring. Therefore, this study seeks to define a trustworthy AI system development maturity model to assist firms in understanding where they stand in terms of developing a trustworthy AI platform. Since trust is time-bound, it is difficult to regain once lost, and this maturity model helps to establish robust controls and governance mechanisms in AI systems from their inception to minimize risk and establish trust. Hence, this study starts by defining the trustworthy enhancing techniques (TET) to build a trustworthy AI system, then advances on to the Trustworthy AI system maturity model (TAS-MM). The study's findings include a maturity model with four stages of trustworthy AI system growth and maturity progression.