Data for AI

CPMAI · 26 questions

• Meridian Regional Airlines' predictive maintenance lead tells the steering committee that the AI initiative's success depends far more on the sensor and maintenance-log data than on which vendor's algorithm the team ultimately picks. Which CPMAI principle does this statement reflect?
• Meridian's cargo-and-demand forecasting initiative ingests booking transactions, real-time weather feeds, and continuous engine-sensor telemetry from the in-service fleet, all arriving at different speeds and in different formats. Which Big Data characteristic is the PM primarily managing when comparing the batch-loaded booking data against the continuously streaming sensor telemetry?
• Meridian's computer-vision ramp-safety initiative has years of raw security-camera footage of the tarmac but no structured records of past foreign-object-debris incidents. Before this footage can train a detection model, what must the project team do to extract usable value from it?
• Two years into building a central repository for all of Meridian's flight, maintenance, and passenger data, the team discovers nobody can find or trust anything in it because data was ingested with no cataloging, quality checks, or access controls. What lesson from prior Big Data implementations does this illustrate?
• Meridian's analytics team currently produces dashboards that report last quarter's on-time performance (descriptive analytics). Leadership now wants to know which upcoming routes are likely to see demand spikes. Which shift in the role of data science does this represent?
• Meridian's engineering team needs to detect an abnormal vibration signature from an aircraft engine within seconds so ground crew can be alerted before the next flight, rather than discovering the anomaly in a report the next morning. Which Big Data approach should the PM push the team toward to enhance this AI capability?
• Meridian's predictive maintenance model needs both the structured numeric telemetry from engine sensors and the semi-structured free-text notes mechanics type into work orders describing what they observed. What does this combination best illustrate about data for AI at Meridian?
• Meridian's loyalty-program data — from initial mileage-transaction capture through model training, production scoring, and eventual archival once accounts close — needs a defined path so nothing is ingested, used, or retired inconsistently. What should the PM ensure is defined to manage this end to end?
• Meridian is standing up its computer-vision ramp-safety program and multiple teams — IT, safety, and ground operations — all touch the camera-footage data differently. Who should the PM ensure is explicitly assigned to own data quality, access rules, and definitions for this dataset?
• Before Meridian's crew-scheduling optimization project begins pulling data from HR, payroll, and FAA duty-time systems, the PM wants retention rules, quality standards, and access permissions agreed upon in writing rather than decided informally as issues arise. What should the PM establish?
• An auditor asks Meridian's AI team to show exactly how a raw sensor reading became a specific input feature used by the predictive-maintenance model, including every transformation it passed through. Which capability must the pipeline have provided for the team to answer this?
• A passenger's name and loyalty number appear slightly differently across Meridian's booking system, the loyalty database, and the customer-service chatbot's records, causing the fraud-detection model to sometimes miss that all three refer to the same person. Which practice should the PM push the team to implement to fix this?
• Meridian's data governance lead publishes a policy stating loyalty-program data must be accurate, complete, and consistent across systems, but six months later nobody has measured whether the data actually meets that policy. What is missing from Meridian's governance approach?
• Meridian's predictive-maintenance program needs engine-sensor readings to keep arriving continuously from in-service aircraft rather than being manually collected in periodic batches uploaded by ground crew. What should the data engineering team design to support this need?
• Meridian's data engineers are building the ingestion-to-model pipeline for the customer-service chatbot and want it optimized specifically for AI workloads rather than reused unmodified from an existing generic reporting-ETL pipeline. What distinguishes an AI-optimized pipeline from a standard business-reporting ETL pipeline in this context?
• Meridian's IT architecture currently couples its data storage tightly to one legacy reporting application, making it hard to add the AI workloads the ramp-safety computer-vision system needs without disrupting existing reports. Which data engineering principle should the PM push the team to apply to the AI infrastructure?
• Meridian's predictive-maintenance model is trained monthly on a large historical archive of sensor readings and maintenance outcomes, but in production it must score a live stream of current sensor readings within seconds to flag an at-risk component. What should the data engineering team build to support both needs?
• Meridian plans to triple its fleet size and add sensors to new aircraft types over the next three years, and leadership wants the predictive-maintenance data architecture to keep working without a redesign each time the fleet grows. What should the PM ensure the data architecture is designed for?
• A new engineer joins Meridian's AI team and struggles to understand how data flows from the engine-sensor feed through several transformation steps into the predictive-maintenance model, because the only documentation lives in the original architect's memory. What should the team have created to prevent this?
• Meridian's fraud-detection pipeline has been running for a year, and the PM wants the pipeline itself, not just the model's output, to surface a warning when the incoming data's format, volume, or statistical properties suddenly change from what the pipeline expects. What is this pipeline-level capability primarily protecting against?
• Meridian's early predictive-maintenance model performs poorly, and investigation reveals the training data included maintenance logs with inconsistent units, missing timestamps, and mislabeled failure events. Which principle explains why the model's poor performance traces directly back to this training data?
• Meridian's engine-sensor data comes from three different sensor vendors, each recording temperature in a different unit and rounding differently, causing the same physical reading to appear as different values depending on the source. What should the data preparation team do first to improve data quality?
• Meridian's finance team already runs a standard monthly data-cleaning process for its budget reports — removing duplicates and fixing obvious typos. The AI team is told to reuse that same process unmodified for preparing labeled training data for the fraud-detection model. What AI-specific data preparation need does this reuse overlook?
• Meridian's demand-forecasting model consistently mispredicts cargo volume on routes affected by severe weather, and the team realizes the training data never included historical weather conditions alongside booking and cargo records. What data preparation technique addresses this gap?
• Meridian's computer-vision model for detecting mishandled baggage performs well in the training environment but struggles on camera footage taken at unusual angles, in poor lighting, or in light rain, conditions underrepresented in the original training set. Which technique should the data preparation team apply to make the model more robust to these conditions?
• Meridian's loyalty-program fraud-detection dataset contains 50,000 legitimate transactions but only 40 confirmed fraud cases, and the resulting model almost never flags anything as fraud because it learned that predicting 'legitimate' is right 99.9% of the time. What should the data preparation team do to address this?