Describe How AI Is Used in Varied Industries CERTIFIED-AI-EXPERT Practice Questions (Page 2)

Questions 6–10

1. 6application · medium

   An agricultural technology company wants to help farmers optimize irrigation and reduce water usage. They have access to satellite imagery, soil moisture sensors, and weather forecasts. The company wants to provide farmers with actionable recommendations on when and how much to water. Which AI application best fits this use case?

   • AA computer vision model that identifies crop diseases from leaf images and recommends specific pesticides.
   • BA natural language processing model that analyzes farmer surveys to understand their irrigation practices.
   • CA robotic harvesting system that uses computer vision to pick ripe crops automatically.
   • DA predictive analytics model that combines soil moisture, weather, and satellite data to recommend optimal irrigation schedules.
   Reveal Solution Discussion Select an answer first
2. 7foundation · easy

   What is a common challenge when implementing AI in the finance industry?

   • ALack of computational power to run AI models
   • BAI models are too slow for real-time fraud detection
   • CEnsuring model interpretability and regulatory compliance
   • DInability to collect any customer data
   Reveal Solution Discussion Select an answer first
4. 8application · medium

   A regional hospital network wants to reduce patient readmission rates by identifying at-risk individuals before discharge. The clinical team has historical electronic health records (EHRs) with diagnoses, lab results, and medication histories. The IT department requires the solution to integrate with existing EHR workflows and provide interpretable predictions so physicians can trust and act on the output. Which AI approach best meets these requirements?

   • AUse a gradient-boosted decision tree with feature importance outputs, integrated into the EHR as a clinical decision-support alert at discharge.
   • BDeploy a deep neural network trained on raw EHR data to predict readmission risk, and integrate the model via an API that returns a risk score.
   • CImplement a generative AI chatbot that interviews patients and summarizes their risk factors for the care team in a daily email.
   • DApply a clustering algorithm to group similar patients and assign readmission risk based on the average outcome of each cluster.
   Reveal Solution Discussion Select an answer first
5. 9application · medium

   A global retail chain wants to use AI to forecast store-level demand for thousands of SKUs to optimize inventory. The company operates in multiple countries with varying holidays, promotions, and local trends. Data scientists have access to historical sales, weather, and promotion data. The business requires forecasts that are updated weekly and can be explained to regional managers. Which approach best addresses the forecasting need while managing the complexity of the data?

   • ABuild separate time-series models for each store-SKU combination using ARIMA, and update them weekly with new sales data.
   • BTrain a single global deep learning model on all stores and SKUs, using country and store as categorical features, and deploy it to generate weekly forecasts.
   • CUse a hierarchical forecasting approach with a gradient-boosted model that includes country, store, SKU, holiday, and weather features, and provide feature importance to regional managers.
   • DImplement a simple moving average per SKU and adjust manually for holidays and promotions each week based on manager input.
   Reveal Solution Discussion Select an answer first
6. 10application · medium

   A telecommunications company wants to use AI to optimize its network performance and reduce customer complaints about dropped calls and slow data. They have network logs, customer location data, and device information. The company wants to proactively identify and resolve network issues before they affect customers. Which AI application best fits this use case?

   • AA customer churn prediction model that identifies subscribers likely to leave due to poor service.
   • BA network optimization model that uses AI to dynamically adjust network parameters (e.g., bandwidth allocation, handover thresholds) based on real-time conditions.
   • CA network anomaly detection model that identifies unusual patterns in network logs and customer complaints to flag potential issues.
   • DA predictive maintenance model that forecasts when network hardware (e.g., cell towers) is likely to fail.
   Reveal Solution Discussion Select an answer first