WebProNews

Recency: Visit Behavior Predicts Visitor Value

Over the past five decades, a lot of research and testing has been done concerning the profiling of customer behavior based on transactional data. The appearance of computers and "data-mining" created the ability to carry on even more extensive studies across a wide range of industries.

The end result? If you had to pick one variable to most universally predict the likelihood of a customer to repeat an action, Recency, or the number of days / weeks that have gone by since a customer completed an action (purchase, log-in, etc.) is the most powerful predictor of the customer repeating this action.

As each day goes by after the customer completed the action, the customer gets less and less likely to repeat it. Plain and simple. You can run all the fancy data-mining scenarios on "likelihood to buy" or "likelihood to visit" you want to - Recency almost always comes up as one of the most important variables in predicting the likelihood of a customer to repeat an action.

Recency is the number one most powerful predictor of future behavior. The more recently a customer has done something, the more likely they are to do it again. Recency can predict the likelihood of purchases, log-ins, game plays, just about any "action-oriented" customer behavior. Recency is why you receive another catalog from the same company shortly after you make your first purchase from them. They know you are most likely to order again immediately after your first order. Recency is the most powerful predictor of future behavior.

The chart on the next page is visitor Recency based on last visit date. The number of unique visitors is on the left (y-axis) scale; the number of days since last visit on the bottom (x-axis) scale. This site has about 5 million unique visitors a month. "Yesterday" is at the far right of the chart - 1 day ago. The left side of the chart is 90 days ago. Customers are plotted by the number of days since their last visit. Look at it for a minute.

What does this data below speak to you?

(click the link below)

http://www.drillingdownbook.com/images/visit-recency.jpg

Visitors by Recency # 1

If your answer is these guys have a great business, you're right. I mean, they have millions of uniques and most of them have visited in the past few days. Not only that, but virtually all of them have visited in the last 10 days! This is a smokin' business. But you wouldn't know that without looking at Recency, would you? You have to know this stuff. It means something very important, not only to marketing, but also to the potential value of your business.

Now, the graph above is a "snapshot" of visitor Recency on a single day; almost all visitors who visited in the past 90 days visited again very Recently. Maybe you don't see the implications; this data is not speaking to you. You're having trouble projecting what this behavior means. I can understand that. You're thinking, "Hey, just because all those folks who last visited over 45 days ago have not come back Recently, that doesn't mean they won't come back in the future. And for that matter, just because a huge group of folks last visited yesterday, that doesn't mean they will come back in the future." Wanna bet?

(click the link below)

http://www.drillingdownbook.com/images/recency-model.jpg

90-Day Revisit Index

Let's take a look at the graph above. I took the same visitors from the first graph and tracked them over the next 90 days, identifying who visited again and who did not by their original Last Visit Date from the first graph. For each of these Last Visit Dates, I created a ratio of those that visited again in the next 90 days to those that did not and created the graph above. If the visit / did not visit ratio was 1 (equal numbers visited and did not visit again), then you don't see a bar on the cart. This occurs mostly in the area labeled "Equilibrium," where folks are just as likely to visit again as not visit again - roughly the area between a Recency of 50 - 60 days in the original graph. A bar above the line means more visitors came back than did not, and the height of the bar indicates how high the ratio of visited again to didn't visit again is. For bars below the line, fewer visitors visited again than didn't visit again.

Look at the overall pattern. Scary how consistent it is, right? If you had to make a bet on who would come back or not, is it pretty clear to you where the odds are in your favor? How about with the visitors on the far right, who are about 438 times more likely to visit again than the visitors on the far left?

You were right with your doubts about Recency above - in an absolute sense. Single out any one visitor and you just might be right - the visitor's Recency does not predict absolutely whether they will come back or not. But you're wrong in a relative sense, as in the likelihood of them to visit again, the odds they will visit again versus other visitors. If you are going to put your money down, make a marketing bet on a visitor or on a customer, you want the odds with you, don't you? You want to put your money down where and when it is more likely you are going to win the marketing bet, don't you?

Further, recall from the first graph that most of the visitor volume is in the more Recent visitor segments. The Revisit Index data above graphs the ratio of people visiting to people not visiting for each daily segment of Recency. But the most Recent segments have millions of visitors; the segments in the Equilibrium area and further to the left have thousands of visitors. So if you are looking for financial impact, both the odds of success and the volume are with you in the more Recent segments.

For fun, take a look at this third graph:

(click the link below)

http://www.drillingdownbook.com/images/bad-recency.jpg

Visitors by Recency # 2

Once again, a graph of customer Recency, based on last visit date. Unique visitors are on the left (y-axis), and days since last visit on the bottom. Yesterday (1 day ago) on the far right, 90 days ago on the far left. This is a smaller site, with a paid subscription business model. They launched with about 60,000 uniques 90 days ago, but only about 3,000 a day come back now. What's the future of this business? What's the data say to you, does it speak?

Just to make sure you didn't forget, what do we know about visitors who are more Recent?

1. The more Recent they are, the more likely they are to respond to promotions

2. The more Recent they are, the higher their potential value to the business

This site is toast, man. Absolutely moribund. They'll be lucky to keep the visitors they have. They need to make major content changes get people to come back to the site. If they don't, there's not much hope. I'd show you the Revisit Index graph for this site, if I had it. They went out of business before I could collect the data to create it. My guess is it would look like this: the most Recent visitors would be about as equally likely to come back as not come back, and it would go straight downhill from there.

These two businesses didn't just magically get to where they were overnight; there was a process, where customer behavior changed over time. If the owners of this site had started tracking visit Recency from the beginning, they would have known they were in trouble before it was too late. And just to be clear, this Recency effect doesn't only apply to visitors to a web site, it applies to any actions customers engage in that create value - purchases, service usage, visits to a office, whatever actions your customers engage in.

Next Article: Recency: Visitor Momentum and Friction

*This article is taken from the book Drilling Down: Turning Customer Data into Profits with a Spreadsheet. The first article in this series can be found here.

Jim Novo has nearly 20 years of experience using customer data to increase profits. He is co-author of The Guide to Web Analytics and author of Drilling Down:Turning Customer Data into Profits with a Spreadsheet. If you want more visitors to take action on your web site, try using the free conversion metrics calculator, downloadable here. If you need to sell more to customers while reducing marketing expenses, get the first nine chapters of the Drilling Down book free at http://www.drillingdownbook.com.
Ask Jim a Traffic Analysis Question!