Today we bring you the third of four excerpts from “Open the Black Box”, OptiMine’s white paper about finding transparency and control in paid-search automation. If you’d like to catch up, you can go here for part 1, and here for part 2. Part 2 was about transparency and how having it adds context to the results your paid-search system is delivering. Today we take the natural next step. Understanding why a system acts is important, but, without control, you are there is little you can to do about it. That’s what today’s post takes a closer look at.
Individual-keyword modeling can produce better performance than clustering, and in most cases, advertisers will be satisfied to let such systems work automatically. But at other times, they will want to take advantage of the keyword-level transparency built into such systems in order to take more direct control based on factors that the software can’t predict. This is why transparency and control are two sides of the same coin, so to speak. Transparency is the ability to see and understand what the software is doing. Control is the ability to apply domain expertise in response to dynamically changing business and market conditions that the software can neither predict nor respond to quickly enough. The best software automation systems not only provide transparency but also anticipate what kind of control analysts will need, giving them maximum flexibility to respond to changing conditions as frequently as
A classic situation is inventory reduction. For example, a retailer has an excess supply of widescreen TVs and plans a big sale for the coming week. The promotion will of course affect clicks, conversion rates, sales, revenue, profitability and other metrics. The software will factor in these changes eventually, but it is likely to react over a number of days rather than immediately at the start of the sale – especially if it weights bid levels based on a seven-day moving average – missing revenue during much of the sale period and wasting money on excessive bids after the promotion is finished. The advertiser knows from experience that during sales of this magnitude, value per click changes by a certain percentage, so bids should be raised by the same percentage during the sale to capture more traffic without sacrificing efficiency or other campaign constraints. The advertiser also knows that after the sale, the software will adjust bids based on data inflated by the sale effect, and so requires the ability to push the bid levels generated by the software down a fraction in order to stay on target.
The ability to take control and “drive” the software is essential for many online retailers to account for short term discontinuities such as special offers and fluctuations in stock levels.
Transparency and control are crucial for achieving paid-search success. Without them, having an automated system is nice, but not much more. The fourth excerpt will conclude this series with a bottom-line look at automation, transparency and control, and how, together, all three can drive significantly improved financial results for your paid-search programs. If you don’t want to wait for excerpt 4, you can download the white paper at OptiMine.com now.