Objective 1.1 Describe How Artificial Intelligence and Machine Learning Are Used to Solve Business (including Commercial, Government, Public Interest, and Research) Problems AIP-210 Practice Questions (Page 3)

Questions 11–15

1. 11foundation · easy

   In drug discovery, ML models are used to predict which chemical compounds are likely to be effective against a disease. This accelerates research by:

   • AAutomating the entire drug manufacturing process
   • BEliminating the need for clinical trials
   • CReplacing the need for domain experts
   • DReducing the number of compounds that need to be tested experimentally
   Reveal Solution Discussion Select an answer first
2. 12foundation · easy

   An e-commerce company uses ML to predict the number of units of a product that will be sold next month to optimize inventory. This is an example of:

   • ARecommendation systems
   • BCustomer segmentation
   • CFraud detection
   • DDemand forecasting
   Reveal Solution Discussion Select an answer first
4. 13application · medium

   A marketing team wants to run a targeted campaign for a new product. They have a large customer database with purchase history, demographics, and website interactions. They want to identify the customers most likely to respond to the campaign to maximize return on their marketing spend. Which AI/ML approach is most appropriate?

   • ATrain a supervised model to predict the probability of a customer responding, and target those with the highest probability.
   • BUse a natural language processing model to analyze customer reviews and find those with positive sentiment.
   • CUse a recommendation system to suggest the new product to all customers who bought similar products before.
   • DUse a clustering algorithm to segment customers into groups and send the campaign to the largest group.
   Reveal Solution Discussion Select an answer first
5. 14expert · hard

   A genomics research institute is studying the genetic basis of a complex disease. They have genomic data for 10,000 patients and a control group. They want to identify which genetic markers are most strongly associated with the disease. They are concerned about the high dimensionality of the data (millions of markers) and the risk of finding false correlations. Which approach is most appropriate?

   • AUse a deep learning model with all markers as input, and interpret the model's weights to find important markers.
   • BUse a clustering algorithm to group patients by their genetic profile and compare the groups.
   • CUse a supervised model with built-in feature selection (e.g., Lasso) to identify a small set of markers most predictive of the disease.
   • DUse a simple correlation test for each marker independently and select all that are statistically significant.
   Reveal Solution Discussion Select an answer first
6. 15application · medium

   A non-profit organization provides legal aid to low-income individuals. They have a large collection of past case documents and their outcomes. They want to help their lawyers quickly find similar past cases to support new cases. Which AI/ML approach is most appropriate?

   • AUse a computer vision model to analyze scanned documents for handwriting.
   • BUse a natural language processing model to create embeddings of the case documents and find similar cases based on semantic similarity.
   • CUse a time-series forecasting model to predict the outcome of the new case.
   • DUse a clustering algorithm to group cases by outcome and only look at cases in the 'won' group.
   Reveal Solution Discussion Select an answer first