December 05, 2013

Attribution: The Future Matters

Here's a typical Attribution challenge.

Maybe you're spending a lot of money on Paid Search. Your Attribution vendor suggests you're overpaying, significantly overpaying for many keywords. So you cut back on spend. You've just "optimized" your business. Good for you!

And then, nine months later, your business is plowing through +2% gains to last year, when you expected +6% gains to last year. Management is upset. Nobody knows why business is not meeting expectations, all anybody knows is that something is just a little bit off.

Here's something that is not well understood about Attribution. When you optimize based on past results, you do not factor in future performance. As a result, future performance is not optimized.

Here's an example - you have a customer with a 40% chance of purchasing again next year. But you are significantly overspending in Paid Search - so you back off numerous terms. For this individual customer, maybe one who likes Paid Search, the repurchase rate changes ... it was 40%, maybe now it is 30%.

If the customer has a 30% chance of purchasing, instead of 40%, then the customer will obviously spend less - and will spend less across the channels the customer prefers (maybe affiliates, maybe email) - since paid search closes sales generated in other channels. In other words, email productivity may suffer because the customer is less active.

Well, it will suffer. I've run a lot of downstream simulations, and that's what I observe.

In other words, the optimization of short-term results via Attribution leads to the sub-optimization of the business in the long-term.

This is a problem that needs a solution. In upcoming posts, we'll talk about the solution.