• For context, when a retailer buys in a clothing item they have to stock it in various sizes. The ratio of stock for each size is referred to as the "size ratio" of the product. E.g. S=0.2, M=0.5, L=0.3
  • I am looking to build a model that predicts the size curve ratio of sales at the end of the season based on data available at the start of the season e.g. historic sales data, product attributes.
  • I am finding it a challenge modelling this scenario because I am used to predicting a single variable, but in this case we are predicting multiple variables which need to add up to 1.

Questions: What is the standard approach to modelling this class of problem? What is the best approach to modelling this?

  • 1
    $\begingroup$ Take a look at Dirichelet regression or fractional multinomial logit models. $\endgroup$ – Dimitriy V. Masterov Jun 22 '18 at 21:51
  • 1
    $\begingroup$ This is a classification problem where the dependent variable has multinomial distribution. Size ratios act as realized probabilities of each "size class". If you have data on many retailers and many characteristics of those, you can start with 1) random forests and 2) gradient boosting with trees. $\endgroup$ – stans Jun 23 '18 at 0:00

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.