Free PMI Certified Professional in Managing AI Practice Questions

CPMAI’s Data Understanding and Data Preparation phases stress that AI success in domains like healthcare depends on robust data pipelines that ensure consistency, quality, and accessibility before modeling begins. Guidance describes these phases as profiling and assessing data, then performing cleaning, transformation, and structuring so that data are reliable and usable by downstream models.

A data quality assessment combined with ETL (extraction, transformation, loading) processes directly supports these objectives. ETL pipelines standardize formats across disparate systems, enforce validation rules, manage missing values, harmonize coding schemes (for example, diagnosis codes), and centralize data into accessible stores. This is exactly the kind of foundational work CPMAI describes as a prerequisite to effective model development, particularly in regulated sectors such as healthcare where inconsistent or inaccessible data can have clinical and regulatory consequences.

By contrast, using NLP to standardize records (B) is a specialized technique that may help later but does not replace a systematic quality and ETL process. Integrating EHR with ML algorithms (C) and designing hybrid cloud storage (D) are more about later technical integration and infrastructure than about defining and ensuring initial data consistency and accessibility. Thus, in line with CPMAI’s data-centric guidance, performing a data quality assessment with ETL processes is the correct method, making option A the best answer.

For an AI-based fraud detection system, PMI-CPMAI–aligned guidance on benefits realization and performance management stresses that success metrics must be quantified against a clear baseline and monitored continuously over time. To properly define and measure KPIs such as detection accuracy, reduced investigation time, and cost savings, the project team should first establish a baseline using historical data comparisons (D). That means analyzing historical fraud cases, prior detection rates, average investigation duration, and historical financial losses to understand “pre-AI” performance. This provides a reference point against which improvements can be measured in a verifiable way.

In addition, PMI-CPMAI emphasizes continuous performance monitoring (B) as part of AI lifecycle governance. Fraud patterns, transaction volumes, and user behavior evolve, so model performance relative to KPIs must be tracked on an ongoing basis using dashboards and periodic evaluations. This supports early detection of performance degradation, allows recalibration of thresholds, and validates that business benefits (e.g., decreased losses, reduced workload) are being sustained.

Relying only on qualitative feedback, random benchmarks, or purely theoretical targets does not meet PMI-CPMAI expectations for evidence-based measurement and governance. Therefore, the two appropriate approaches are: implementing a continuous performance monitoring system (B) and establishing a baseline using historical data comparisons (D).