Forecasting from Similar Products

Overview


One of the primary methods of forecasting a customers rating of a product is to find other products similar to the given product, and taking an average of that customers ratings for the product in question. (see nearest neighbor method)

Determining Similarity


A central task in the method is to find a function (a kernel) which can compute a measure of similarity between two customers. This function will be used to

  • Feature Based - if a set of features for each product is available , then a kernel can be constructed from those features. Of course, determining the form of the function (finding the optimal function) is the challenge
  • Latent Factors

Similarity Measures


Similarity Measures