Previous Section
Peter gave a nice lead for what I'm going to talk about today. Because essentially what we have are individuals, or in this case, individual stores, and for each of these stores we want to try to relate to some action -- in this case a decision that's going to made in the pricing context. Just to let you know, I'd like to acknowledge that this research comes from, the hyper-marketing project at the University of Chicago.
The talk today is basically split into three parts. The first part is to really discuss what micro-marketing is and to explain one of the data sources and the decision the retailer is going to make. The next is to try to think about how we can model store level demand in this hierarchical Bayesian model. Finally, I'm going to illustrate, now that we've gone out and measured store local demand, how that is mapped back into the retailer's profit function (which in turn decides what is the retailer going to charge for his prices).
Go to written version of paper