CFA Level I · CFA Level I Exam · Introduction to Financial Data Science
An analyst's dataset of customer incomes contains several extreme values far above the rest, and the analyst wants to reduce the influence of these values without deleting the observations. The most appropriate data preparation step is:
Winsorization is most appropriate. It replaces extreme values with a chosen percentile cutoff, so the observations stay in the dataset but their influence on results is reduced. Trimming deletes the outliers, and one-hot encoding is used to convert categorical variables into binary features.
- AwinsorizationCorrect
- Btrimming
- Cone-hot encoding
Explanation
Winsorization replaces extreme values with specified percentile values, retaining the observations while limiting their influence. Trimming removes the extreme observations altogether, which the analyst wants to avoid. One-hot encoding converts categorical variables and does not address outliers.
Did you get it right without looking?
One question tells you little. A timed set on Introduction to Financial Data Science shows your real accuracy, how long you take and where you lose marks.
More Introduction to Financial Data Science questions
- An analyst applies a clustering algorithm to the return histories of 500 stocks to find groups that behave similarly, without predefining an…
- An analyst builds a bag-of-words document term matrix from 2,000 corporate disclosures to predict whether a firm will cut its dividend. Comp…
- An analyst prepares text data from company filings for a model and removes common words such as 'the', 'and', and 'of' before counting word …
- A data scientist converts a column of text analyst comments into numerical features that a machine learning model can use. Which step in tex…
- A researcher wants to show the distribution, median, quartiles and outliers of monthly returns for several funds side by side. The visualiza…
- A model predicting loan defaults achieves very low error on the training data but performs poorly on new data. This outcome is best describe…