The keys challenges in implementing cognitive testing include the following:
Need for training the system: The system needs to be trained in the domain and application landscape, and this requires a significant investment in terms of time and effort during initial stages. However, there are great economies of scale once the system is trained, and the costs come down sharply.
Incorrect Requirements: The cognitive computing system derives its intelligence from the requirements that are fed into the system. The challenges with incorrect requirements (lack of alignment with customer needs; ambiguous /inaccurate/invalid/infeasible requirements) could lead to incorrect test results.
Complex Architecture: This challenge combined with the frequent technology and configuration changes pose technical challenges in implementing this technology.