We recently built a historical model based on the linear regression and stepwise tools. The goal here is to determine the most meaningful stats categories over time for a specific location. Lets describe these as Category 1, Category 2, Category 3, Category 4 and Category 5. The dependent variable is the performance rank of the products at this location. ie. 1, 2, 3, 4, etc. The product is irrelevant in this dataset. Our interest is determining the independent variables that have the highest predictive value in determining the ranked performance of the products at that location.
The next step in the workflow would be to use the categories to predict the rank of a different set of products. The new data set includes the stats categories from the Stepwise tool for Category 1, Category 2, Category 3, Category 4 and Category 5 but with the data from the new location. Using this data we'd like to rank the new data. The question is how do we associate the new product names with the ranks predicted in the new dataset since the new product names have no relevancy in the historical data set but are required for the final predictions.
Any guidance would be appreciated.
