Machine Learning - Ordinal target variable

CFA Level II
#1

Step 3
For each of the 20 different groups, we use labeled data to train a model that will predict the five stocks (in any given group) that are most likely to become acquisition targets in the next one year.

Q. The target variable for the labelled training data to be used in Step 3 is most likely which one of the following?

  1. A.A continuous target variable.
  2. B.A categorical target variable.
  3. C.An ordinal target variable.

Solution

B is correct. To predict which stocks are likely to become acquisition targets, the ML model would need to be trained on categorical labelled data having the following two categories: “0” for “not acquisition target”, and “1” for “acquisition target”.

A is incorrect, because the target variable is categorical, not continuous.

C is incorrect, because the target variable is categorical, not ordinal (i.e., 1st, 2nd, 3rd, etc.).

I would like to ask why the answer to this question is not C when we are predicting the 5 most likely stocks to become acquisition targets (i.e there is ranking involved).

#2

It’s not a well-worded question.

It appears that it’s meant to tell you that these five stocks (in no particular order) are the most likely targets. They’re focusing on the “in no particular order” part.

Questions on the real exam will be quite clear.

2 Likes
#3

Is it fair to say that if “in no particular order” is not crucial, the target variable could be continuous too? I.e., probability of being acquired

#4

Nope.

#5

Hmm, but why not? @S2000magician

#6

The question isn’t asking for the probabilities of acquiring the companies. It’s asking for the top five companies on the list. For each company, that’s simply a yes/no question: it’s in the top 5, or else it’s not.

#7

But if the question says “most likely”, and we have the 5 companies that have the highest probability, doesn’t that answer the question too?

#8

Yes, but the answer is the companies themselves (e.g., their names, or their ticker symbols), not the probability of their being acquired.

#9

OK, I guess I thought that if we can rank the companies by probabilities, we have the names too. Thanks anyway @S2000magician

#10

My pleasure.