Look-Back Periods in Paid Search

By — 05.31.11

Lookback

The goal of paid search management is to predict the future. To do that, PPC tools need to look at the past. The question is, How far back should they look? Let’s first review what the systems are looking at. In most bid management systems, the formula for calculating the actual (not maximum) cost per click (CPC) is:

CPC = (AOV × CVR) ÷ ROAS

Average Order Value (AOV) and Conversion Rate (CVR) are based on sampling historic performance, while Return on Ad Spend (ROAS) is typically a fixed value specified by the retailer. Most technologies will allow you to specify different ROAS or A/S goals for different keyword segments. Over time, AOV and CVR change—and in some cases very quickly—due to many factors. One critical factor is seasonality. Take the example of DVDs. During most of the year, demand for DVDs is relatively flat, so AOV and CVR don’t move much. But DVDs are a popular Christmas gift, so demand for DVDs—and thus CVRs—begin to climb in mid-November, hitting a peak just before Christmas. Then CVRs plummet.

Past vs. Future Data

Most bid management systems only look at the recent past to make bid optimization decisions and are blind to upcoming trends.

Where Bid Management Systems Go Wrong

Without knowing that this is a recurring pattern, how do bid management systems compute the “correct” CPC for DVDs in January, or any other month? The short answer: they don’t. The majority of systems look at a fixed length of trailing data—a look-back period (LBP)—which typically ranges from 30 to 180 days. Returning to the DVD example, if it’s January and the LBP is 60 days, most systems will predict that the progressively climbing CVRs observed during November and December will continue to stay strong, and thus in response keep CPCs high. That would obviously be the wrong thing to do. Likewise, if the system looked at six months of data prior to November, it wouldn’t predict the upcoming seasonal sales spike and would thus keep CPCs too low during the holiday shopping season. Again, the wrong thing to do. What, then, is the right LBP?

Determining the Appropriate LBP

The LBP needs to be just long enough to obtain statistically significant data—no longer, no less. The longer you look back, the less recency the data has, which reduces its potential to accurately predict the future. But to obtain sufficient data, the LBP might need to be quite long. The key issue is that one size does not fit all. The appropriate LBP will vary based on product type and by keyword. It should be based on how much recent historic data is available, normalized by what seasonal patterns are expected for this type of keyword. The LBP for DVDs, for instance, may be to the same period one year prior. For other products with high-volume keywords, it may be much shorter. For example, if October historical information (for this year) indicates that a DVD is going to have a conversion rate of four percent, and we know that this type of DVD shows a doubling of conversion rates from October to the end of November, we can predict that this DVD will have a conversion rate close to eight percent.

The Long Tail, Latency and Roll-Ups

Adlucent’s Deep Search™ software platform factors in several other issues that affect LBPs. Consider long-tail products and their keywords. Clicks on keywords for products far down the tail may be so infrequent—say, once every 30 days—that it takes months to compile sufficient data for predictive purposes. In fact, the majority of keywords don’t generate a lot data within a short period of time. Deep Search thus determines the appropriate LBP on a per-keyword basis. Other systems struggle with such low-trafficked keywords because certain short LBPs would indicate the keyword hasn’t sold any volume at all. Another factor is a latency effect due to AOVs. Consumers research (shop for) higher AOV products for longer periods of time. For these products, you need a longer LBP, otherwise it may seem that keywords aren’t effective when in fact they are—if you look at a sufficient period of time. While “past performance in no guarantee of future results,” it’s still an important variable in predicting what will happen tomorrow. The trick is to appreciate that how far you look back can have significant impacts on the success of paid search programs. Determining unique LBPs on a keyword-level basis and factoring-in issues such as seasonality and AOV latency will also dramatically improve the model.

3 Responses

  1. Boston says:

    I work for a retailer that has partnered with Adlucent for nearly two years. Together, we have managed our SEM channel to drive top line revenue, to drive new customer acquisition, and most recently, to drive a very robust contribution. In the contribution mode, we had a strict new customer cost that we wanted to shrink by 75% compared to the revenue generation mode.

    The Adlucent team used a customized look-back period for our account that was different from the standard look-back period that Michael refers to. The customized look-back period was a huge contributor to achieving the challenging new customer cost and the contribution that we were driving towards. We hit the new customer cost and Adlucent still hit our revenue goals, which were 15%-20% higher year-over-year. Additionally, our A/S was cut in half.

    The LBP discussion here is not just opinion. Michael and Adlucent have put this search prose into action and have made it work for a top 150 Google spender.

  2. Boston,

    Thank you for sharing the results you’ve seen using multiple, custom look-back periods in your SEM program. We are posting an article on seasonality next week that you may find interesting as well. With retail paid search, it’s just as important to look back to the previous year as it is to look at recent history. Having custom algorithms to proactively anticipate changes due to seasonality is critical.

    Thanks again for sharing.

  3. [...] Adlucent realized long ago that retail is different from other verticals. The kinds of products e-tailers sell are very different than, say, what travel agents, financial firms, or auto manufacturers sell online. The differences in the products they sell lead to major differences in how buyers of these products shop, which in turn dictates how their algorithms should be developed. For instance, customers spend far less time shopping online for a DVD than they do for a car. These faster purchase cycles mean that most retailers’ algorithms should use a shorter look-back period. [...]

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>

About Us

Adlucent is a performance-based marketing technology and analytics company focused on helping Retail and Ecommerce companies deliver relevant advertising that converts.

Contact Us

Adlucent
2130 S Congress Ave
Austin, TX 78704
1.800.788.9152
solutions@adlucent.com

BuyerPath™

BuyerPath™ platform is an advanced shopping analytics platform leveraging query data, in-market data, CRM data and online/offline shopper demographics to help retailers find, value, align and maximize valuable ad moments for optimal return
Scroll to top