Data Issues DY0-001 Practice Questions (Page 1)

Questions 1–5

1. 1application · medium

   A data analyst is working with customer feedback data that includes ratings on a 1–5 scale. The business wants to analyze overall satisfaction trends. What is the most appropriate way to handle the granularity of this data?

   • AConvert the ratings to a continuous scale by taking the mean.
   • BTreat the ratings as ordinal categorical data and use appropriate models.
   • CRemove ratings of 1 and 5 as outliers.
   • DAggregate the ratings into two categories: positive and negative.
   Reveal Solution Discussion Select an answer first
2. 2foundation · easy

   Which of the following is a common method to incorporate seasonality into a predictive model?

   • ARandomly shuffling the data before training
   • BAdding seasonal dummy variables to the model
   • CUsing only linear regression without any time features
   • DRemoving all time-related features from the dataset
   Reveal Solution Discussion Select an answer first
4. 3expert · hard

   A data scientist is modeling the relationship between employee satisfaction score and productivity. The scatter plot shows a clear non-linear pattern: productivity increases with satisfaction up to a point, then decreases (inverted U). A linear model has poor fit. The dataset also contains a few employees with extremely low satisfaction and very high productivity, which are unusual but valid. What is the best approach?

   • AAdd a squared satisfaction term and use robust regression to reduce the influence of the unusual points.
   • BApply a log transformation to satisfaction and productivity.
   • CUse a simple linear regression with satisfaction only.
   • DRemove the unusual employees and then fit a linear model.
   Reveal Solution Discussion Select an answer first
5. 4foundation · easy

   A dataset contains daily sales figures, but the analysis requires monthly totals. What is the process of converting the data to a coarser level of detail called?

   • AAggregation
   • BDisaggregation
   • CNormalization
   • DSampling
   Reveal Solution Discussion Select an answer first
6. 5application · medium

   A data analyst is building a model to predict rare equipment failures. The dataset has thousands of normal operations but only a few failure events. The model rarely predicts failures. What is the most effective way to improve the model's ability to detect failures?

   • AIncrease the model's complexity by adding more features.
   • BUse a larger test set to evaluate performance.
   • CUse oversampling techniques like SMOTE to create synthetic failure examples.
   • DRemove normal operations to balance the dataset.
   Reveal Solution Discussion Select an answer first