I'm trying to make a model to predict the gross income of our company's stores based off of a 14-feature data monthly data set that I have for each store. We have 950 stores.
I have no problem shaping the dataset to feed one store's data into the model and make predictions on that store's timeline. I have no idea how to shape the data though to train the model on all of the store's data, so I'm not just training on individual store.
Is this possible? I saw this question which seemed relevant, which suggests adding the store ID as a feature to the data set. Wouldn't the input then just be something like (950, N, 15) where N is how many months of data I have? Is this a simple matter of setting the batch_size?
I'm using tensorflow to build this, and have been working off of this example / tutorial
I'm fairly new to ML. Thanks!
