AppliedMultiple choiceFree solution
Why does an interviewer ask for a baseline before you describe your model?
- ATo check whether you can implement something simple quickly
- BTo see whether you know what your model must beat
- CBecause simple models are always better on real data
- DTo fill time at the start of the interview
Show the answer and worked solution
Answer: B – To see whether you know what your model must beat
The baseline is what your model must beat, so without it no improvement can be stated. In a demand problem yesterday’s value or a day-of-week seasonal mean is a formidable competitor, and models often fail to beat one. Quoting your model’s error alone credits it with everything the naive rule already delivered, and the honest claim is the gap between the two. Establishing the baseline first also gives you a fallback that ships, which is worth saying out loud.
- A. Implementation speed is not what is being scored.
- B. Correct. Yesterday’s value or a seasonal mean is a formidable competitor, and beating it is the actual claim.
- C. Often, not always – and the baseline is how you find out which.
- D. It is one of the most heavily weighted parts of a case.
Takeaway: A baseline is what your model has to beat, not a formality.
Answer it in practice – your answer is marked and recorded.
Learn the method
More research case studies questions
- You are asked to "predict demand" for a bike-share operator. What do you say first?Foundation
- Your evaluation metric is mean absolute error and the target is heavily skewed.Foundation
- You forecast demand to decide inventory, where being short costs four times as…Applied
- You are asked to predict house prices, which range from tens of thousands to…Applied
- A target takes values 1,2,3,4,100.Applied
- How many independent observations are needed to detect an information…Advanced