A project manager is reviewing the performance of an AI model used for predictive analytics in sales. The model's accuracy is within acceptable limits; however, its precision is low. What is the cause for the precision issue?
Correct Answer: B
In AI classification problems, PMI-CPMAI highlights the importance of understanding multiple performance metrics-accuracy, precision, recall, F1, and others-rather than relying on accuracy alone. Precision measures, out of all predicted positive cases, how many are actually positive. Low precision means a high proportion of false positives. It is possible for a model to have acceptable overall accuracy while still having low precision, especially when the underlying data is class-imbalanced. When the training data is unbalanced-typically many more negative than positive cases-the model can achieve high accuracy simply by classifying most instances as the majority class. However, its behavior on the minority (often the more important) class can be poor, leading either to many false positives or false negatives, depending on thresholds and training dynamics. PMI-CPMAI treats data distribution analysis and class balance as core elements of data quality assessment because skewed data often manifests as misaligned metrics: accuracy looks fine, while precision or recall is deficient. Underfitting or overfitting usually depress both accuracy and other metrics and would more likely show broader performance problems. Flawed feature selection can harm performance generally, but the classic and most direct cause tied to the pattern "accuracy OK, precision low" in exam-style reasoning is unbalanced training data, making option B the best explanation.
Question 67
A logistics company is operationalizing an AI solution to optimize delivery routes. The project manager needs to gather up-to-date information on traffic patterns, delivery schedules, and vehicle performance. Which method will integrate these diverse data types?
Correct Answer: B
In CPMAI and PMI-aligned AI lifecycles, integrating diverse data types from multiple operational systems is typically handled through robust data engineering pipelines, most commonly implemented as ETL (extract, transform, load) or closely related ELT patterns. For a logistics optimization use case, the AI system needs to bring together traffic patterns (often from external or sensor feeds), internal delivery schedules, and vehicle performance/telematics data into a consistent, analyzable structure. An ETL pipeline is designed precisely for this: it extracts data from heterogeneous sources, transforms it into common formats and schemas (handling units, timestamps, geocodes, data quality rules), and loads it into a target store (data lake, warehouse, or feature store) that downstream AI components can consume. CPMAI emphasizes that this integration work is a core part of the Data Understanding and Data Preparation phases, because AI models depend on unified, high-quality inputs rather than fragmented, siloed feeds. While real- time frameworks, federated models, or warehouses may play additional roles, the primary method explicitly focused on integrating diverse data sources into a coherent whole is an ETL pipeline, making option B the best fit.
Question 68
During the transition to an AI solution, the project manager discovers that certain tasks may not require cognitive AI capabilities and can be handled through traditional automation methods. As a result, the project team starts segregating tasks based on their cognitive requirements. What should the team consider?
Correct Answer: C
PMI-CPMAI clearly distinguishes between cognitive AI capabilities and traditional automation or noncognitive solutions. The guidance stresses that not every task in a workflow benefits from AI and that "project leaders should deliberately match solution complexity to problem complexity, reserving cognitive AI for tasks that truly require perception, learning, or sophisticated decision support." For deterministic, rule- based, repetitive tasks, the recommended approach is to use conventional automation technologies (scripts, RPA, rule engines, workflow systems) rather than machine learning models. When a project team discovers that certain tasks do not require cognition (e.g., simple routing, format conversion, deterministic validations), PMI-CPMAI recommends "segregating cognitive from noncognitive tasks and applying the simplest effective technology to each." This reduces cost, operational risk, and technical debt, while focusing AI engineering effort where it provides differentiated value. Applying AI to noncognitive tasks can introduce unnecessary complexity, additional monitoring and governance overhead, and avoidable model risk. Proceeding only with intelligent functionalities or overanalyzing traditional tasks without acting on the insight misses this key optimization. Therefore, once tasks have been segregated by cognitive requirements, the team should utilize traditional automation solutions for noncognitive tasks and focus AI design, data, and model work only where cognitive capabilities are justified. This aligns with PMI-CPMAI's principle of "fit-for-purpose" technology selection and responsible, efficient AI adoption.
