An abstract iFortis Worldwide brand visual, a lit data plane receding to a horizon

Glossary

What is Explainability?

Definition. Explainability is the ability to show, in terms a person can follow, why an AI system produced a particular output or decision.

Explainability in practice

It matters most where decisions affect customers, money or safety. In practice it combines model techniques with recorded evidence of the data and rules used.

Where iFortis Worldwide applies it

See AI Security, Trust and Governance for how this is used in client work.

Related terms

  • Audit trail: An audit trail is a time-ordered record of who or what did something, when, on what data and with what result.
  • Responsible AI: Responsible AI is the practice of developing and using AI in ways that are fair, transparent, safe, private and accountable.
  • Model risk management: Model risk management is the governance of risks that arise when decisions rely on models, including errors, bias and misuse.

All glossary terms

An abstract iFortis Worldwide brand visual, a lit data plane receding to a horizon

Want these ideas applied to your business?

Start with a focused opportunity assessment. We find where AI creates measurable advantage and what it takes to get there.

Contact us Submit an RFQ