-1

This concerns a "software algorithm" from https://stackoverflow.com/help/on-topic

I am working on a problem(non competition) from hacker rank https://www.hackerrank.com/challenges/predict-missing-grade

Basically you're given test data of a bunch of students of their scores in other subjects not including math and you are to predict their score in math based off all their other test scores. Say you were passed data of

{"SerialNumber":1,"English":1,"Physics":2,"Chemistry":3,"ComputerScience":2}

How would you go about generating that student's score in mathematics or coming up with a prediction engine to generate the math score? I know that's the whole point of this question but can someone give me a hint or a resource to go to so I can have a chance of figuring this out and actually get started? I really want to learn.

Community
  • 1
  • 1
committedandroider
  • 8,711
  • 14
  • 71
  • 126

1 Answers1

0

There are a lot of possible strategies to do this, the purpose in asking the question seems to be to try to determine which works the best.

It seems impossible to get 100% correct, so the goal is really to come up with a strategy that provides the correct answer more often than not, and hopefully beats the current best. On that note, the best at the time of writing, seems to give about 46% more correct answers than wrong ones, if I'm reading the scoring right.

A quick glance at the first few training numbers and looks like the English score might be a good indicator of the Mathematics score. The reason being that it seems to often be within 1 of the English score (English Score + 1 seems to yield slightly better results). Thus a simple strategy might be to simply return the English score as the Mathematics score. However, you'd want to go through the data and see if that is actually the case that the Mathematics score is within 1 of the English score more often than not This ends up looking to be significantly better than random, but roughly equal in terms of correct VS wrong answers, so it would need to be improved upon by a fair bit to get close to the current best. So you then might want to look into what the other scores look like when using the English score would be counted as wrong. Alternatively, you could look for a different indicator.

Nuclearman
  • 5,029
  • 1
  • 19
  • 35