Imagine you have a dataset of rower lap-times with several predictor variables, such as weight, benchpress, deadlift, squat, nutrition quality, etc.

Now, let's say for a given rower, you want to reduce her lap time, but you can only train along ONE DIMENSION. How would you identify the best predictor to optimize? Assume only 1 standard deviation of improvement is possible.

I'm trying to think beyond brute force methods, here. Which family of machine learning algorithms would be best for this type of problem, and how would you attack it?


  • $\begingroup$ Seems like a very unrealistic set-up - e.g. do you really think weight would not g $\endgroup$ – Björn Jul 19 '17 at 7:18
  • $\begingroup$ go up for those that can benchpress more? $\endgroup$ – Björn Jul 19 '17 at 7:19
  • $\begingroup$ One could train for motor unit recruitment rather than mass gain. That said, I think this general type of problem (prescribing an optimal treatment) pops up everywhere, and I'd like to see an elegant way of approaching it. $\endgroup$ – MattY Jul 19 '17 at 7:47

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.