SDS Problem identification and data readiness

In a data science project, the first stage of CRISP-ML is:

• 1 Monitoring
• 2 Business and data understanding
• 3 Deployment
• 4 Modelling

Which statement describes a well-scoped data science problem?

• 1 It starts with the choice of algorithm
• 2 It has no stakeholders
• 3 It states a specific decision, a measure of success and the data available
• 4 It says 'use AI to improve results'

A data quality audit would check completeness, accuracy, consistency and:

• 1 The server brand
• 2 The number of users
• 3 Timeliness and validity
• 4 The colour of the charts

A model is built on five years of customer data collected only from branch customers, and will be used for online customers. The main concern is:

• 1 The model is too fast
• 2 The users are too many
• 3 The data may not be representative
• 4 The data is too clean

A deployed model's accuracy falls over time because customer behaviour has changed. This is called:

• 1 Underfitting
• 2 Data leakage
• 3 Model drift
• 4 Overfitting

Early stakeholder engagement in a data science project is important mainly because it:

• 1 Reduces the need for data
• 2 Allows the team to avoid documentation
• 3 Ensures that the work addresses a real need and increases the chance the result is used
• 4 Avoids all risk

Which of these is a data preparation task?

• 1 Handling missing values and encoding categories
• 2 Presenting results to the board
• 3 Monitoring drift
• 4 Agreeing the problem