A new approach to select the best subset of predictors in linear regression modelling: bi-objective mixed integer linear programming

Hadi Charkhgard, Ali Eshragh


We study the problem of choosing the best subset of features in linear regression, given observations. This problem naturally contains two objective functions including minimizing the amount of bias and minimizing the number of predictors. The existing approaches transform the problem into a single-objective optimization problem. We explain the main weaknesses of existing approaches and, to overcome their drawbacks, we propose a bi-objective mixed integer linear programming approach. A computational study shows the efficacy of the proposed approach.



linear regression, best subset selection, bi-objective mixed integer linear programming.

DOI: http://dx.doi.org/10.21914/anziamj.v61i0.12784

For new registrations: currently (May 2019) there is
a problem with the Captcha Validation. Until we fix, please
email editor@journal.austms.org.au and request

Remember, for most actions you have to record/upload into this online system
and then inform the editor/author via clicking on an email icon or Completion button.
ANZIAM Journal, ISSN 1446-8735, copyright Australian Mathematical Society.