Skip to content

CFA Level I · CFA Level I Exam · Introduction to Financial Data Science

An analyst builds a term frequency-inverse document frequency (TF-IDF) measure for a corpus of 1,000 earnings call transcripts. The word "revenue" appears in nearly every transcript, while "restructuring" appears in only a few transcripts, and both appear equally often in a particular transcript. Compared with "revenue", the TF-IDF score of "restructuring" in that transcript is most likely:

The score for "restructuring" is higher. TF-IDF multiplies term frequency by inverse document frequency, which rises when a word appears in few documents. With equal term frequency, the rare word receives a larger weight than "revenue", which appears almost everywhere.

  1. Aequal, because term frequency is the same for both words
  2. Blower, because rarer words are penalized by the inverse document frequency
  3. Chigher, because the inverse document frequency is larger for words found in few documentsCorrect

Explanation

TF-IDF multiplies term frequency by inverse document frequency. Equal term frequency leaves IDF as the difference, and IDF is larger for words found in few documents. So "restructuring" scores higher, and the equal option ignores IDF.

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.

Practise Introduction to Financial Data ScienceFree diagnostic mock

More Introduction to Financial Data Science questions