0
$\begingroup$

Suppose two firms are operating in the same field (e.g. insurance). If firm 1 knows which features firm 2 is using in their model, can firm 1 improve its model using that information?

What if firm 1 knew the weight/importance of those features as well?

Improve this question
$\endgroup$
2
  • $\begingroup$ Does Firm 1 also know that Firm 2 has better (more numerous, more precise,etc.) data and believes that Firm 2 is incapable of making mistakes? Do the Firms compete in the same market with the same products? The question as it stands is not well posed. $\endgroup$
    – JTH
    May 24, 2020 at 22:36
  • $\begingroup$ @JTH Yes, as the question says: both firms compete in the same field. However, the precision/accuracy/etc of firm 2 is not known to firm 1. $\endgroup$
    – Behnam Moh
    May 24, 2020 at 22:57

1 Answer 1

Reset to default
0
$\begingroup$

This would be awesome! In fact it would be even better, if the firm would know how the weights would have been generated (for example if the weights might be biased due to ridge regression/lasso).

This knowledge could be added in various ML models as some kind of "pre-knowledge" for example in a Baysian Framework. Or just be used as a guidline in model building based an theoretical assumptions (doing this well reduces variance, so there is less need for the introduction of bias in data driven model selection/penalizing).

Improve this answer
$\endgroup$
3
  • $\begingroup$ Thank you for your insight! I'm curious to know about the Bayesian Framework that you mentioned. Can you elaborate on that or suggest resources that mention that? $\endgroup$
    – Behnam Moh
    May 24, 2020 at 23:00
  • $\begingroup$ I think an detailed explaination would go to far here: but you can take a look in the wikipedia for a first impression en.wikipedia.org/wiki/Bayesian_inference In fact baystian statistic is a different view on statistics. $\endgroup$
    – platypus
    May 25, 2020 at 11:54
  • $\begingroup$ I see, yes I am familiar with Bayesian statistics. However, I'm curious to know how one can use the "pre-knowledge" about another firm's features in order to form a more accurate ML model. $\endgroup$
    – Behnam Moh
    May 25, 2020 at 13:14

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.