Machine Learning Quiz

A retail company wants to predict customer churn based on past purchase behavior, customer service interactions, and demographic data. Which type of machine learning problem is this?

• Unsupervised learning - clustering

• Supervised learning - classification

• Supervised learning - regression

• Reinforcement learning

What is the main goal of supervised learning?

• To find hidden patterns in data without labeled output

• To predict outcomes based on labeled input-output pairs

• To reduce dimensionality of data

• To cluster data into groups

Which of the following best describes the difference between classification and regression?

• Classification predicts numerical outcomes, while regression predicts categorical outcomes

• Regression predicts numerical outcomes, while classification predicts categorical outcomes

• Regression clusters data, while classification reduces dimensions

• Classification uses unsupervised learning, while regression uses supervised learning

In a data science project, after data cleaning, what is typically the next step?

• Training the model

• Feature engineering

• Algorithm selection

• Evaluation

Which of the following is an example of a real-life use case for classification?

• Predicting future sales revenue of a company

• Predicting whether an email is spam or not spam

• Forecasting next week's weather temperature

• Identifying clusters of customers based on buying habits

You are tasked with predicting housing prices in different neighborhoods based on features like square footage, number of bedrooms, and location. Which type of model would you use?

• Classification

• Clustering

• Regression

• Reinforcement learning

In unsupervised learning, which of the following techniques is commonly used to group data?

• Decision trees

• Clustering

• Linear regression

• K-nearest neighbors

Which of the following would be considered a practical application of unsupervised learning?

• Detecting fraudulent insurance claims using labeled past data

• Grouping customers based on their purchasing behavior to identify market segments

• Predicting stock prices for next quarter

• Classifying emails as spam or not spam

When deploying a machine learning model to production, which of the following practices are recommended? (Select all that apply)

• Monitor model performance over time for drift

• Deploy without version control to speed up the process

• Implement automated retraining pipelines

• Set up logging and alerting systems

A model predicting customer lifetime value shows good performance metrics but performs poorly in production. What could be the reason(s)? (Select all that apply)

• Training data doesn't represent current customer behavior

• Feature engineering pipeline differs between training and production

• Model is too simple

• Concept drift in customer behavior patterns