AI-900 Comprehensive Quiz 1

A company employs a team of customer service agents to provide telephone and email support to customers. The company develops a webchat bot to provide automated answers to common customer queries. Which business benefit should the company expect as a result of creating the webchat bot solution?

• increased sales

• a reduced workload for the customer service agents

• improved product reliability

• enhanced marketing strategies

Answer explanation

The webchat bot automates responses to common queries, which reduces the number of inquiries customer service agents handle, leading to a reduced workload for them.

For a machine learning process, how should you split data for training and evaluation?

• Use features for training and labels for evaluation.

• Randomly split the data into rows for training and rows for evaluation.

• Use labels for training and features for evaluation.

• Randomly split the data into columns for training and columns for evaluation.

Answer explanation

The correct choice is to randomly split the data into rows for training and rows for evaluation. This ensures that both sets are representative of the overall dataset, allowing for effective model training and unbiased evaluation.

How many correctly predicted positives are there according to the confusion matrix?

• 5

• 11

• 1,033

• 13,951

Answer explanation

The confusion matrix indicates the number of true positives, which are the correctly predicted positives. In this case, the value is 1,033, making it the correct answer.

How many false negatives are there according to the confusion matrix?

• 5

• 11

• 1,033

• 13,951

Answer explanation

In a confusion matrix, false negatives are the instances where the model incorrectly predicts a negative class when the true class is positive. Here, the count of false negatives is 5, making it the correct answer.

You build a machine learning model using the automated machine learning user interface (UI). You need to ensure that the model meets the Microsoft transparency principle for responsible AI. What should you do?

• Set Validation type to Auto.

• Enable Explain best model.

• Set Primary metric to accuracy.

• Set Max concurrent iterations to 0.

Answer explanation

Enabling 'Explain best model' provides insights into the model's decisions, aligning with Microsoft's transparency principle for responsible AI. This choice enhances understanding and accountability in AI outcomes.

Is forecasting housing prices based on historical data an example of anomaly detection?

• Yes

• No

• Sometimes

• Only in specific cases

Answer explanation

No, forecasting housing prices based on historical data is not anomaly detection. Anomaly detection focuses on identifying unusual patterns or outliers, while forecasting aims to predict future values based on trends in the data.

Is identifying suspicious sign-ins by looking for deviations from usual patterns an example of anomaly detection?

• Yes

• No

• Only for financial systems

• Only for healthcare systems

Answer explanation

Yes, identifying suspicious sign-ins by looking for deviations from usual patterns is a classic example of anomaly detection, as it involves recognizing unusual behavior that differs from established norms.

Is predicting whether a patient will develop diabetes based on the patient's medical history an example of anomaly detection?

• Yes

• No

• Only if the patient has a family history of diabetes

• Only if the patient is over a certain age

Answer explanation

No, predicting diabetes based on medical history is not anomaly detection. Anomaly detection identifies unusual patterns, while this prediction uses historical data to assess risk, which is a classification task.

Which AI workload type is used for an automated chat to answer questions about refunds and exchanges?

• Anomaly detection

• Computer vision

• Conversational AI

• Knowledge mining

Answer explanation

Conversational AI is designed for automated interactions, such as chatbots that handle inquiries about refunds and exchanges, making it the correct choice for this workload type.

What AI workload type is used for determining whether a photo contains a person?

• Natural language processing

• Computer vision

• Anomaly detection

• Knowledge mining

Answer explanation

The correct choice is 'Computer vision' because it involves analyzing images to identify objects, such as determining if a photo contains a person. Natural language processing deals with text, while anomaly detection and knowledge mining are unrelated.