CoolData blog

2 December 2010

Call attempt limits? You need propensity scores

Filed under: Annual Giving, Phonathon, Predictive scores — Tags: , , — kevinmacdonell @ 4:51 pm

A couple of weeks ago I shared some early results from our calling program that showed how very high-scoring alumni (for propensity to give by phone) can be counted on to give, and give generously, even after multiple attempts to reach them. If they have a high score, keep calling them! Yes, contact rates will decline, for sure. But these prospects are still likely to give if you can get them on the phone, making the extra effort worthwhile.

For the other three-quarters of your prospects, it’s a different story. You may still want to call them, but keeping those phones ringing all year long is not going to pay off, even if you have the luxury of being able to do so.

This is ground I’ve already covered, but I think it bears repeating, and I’ve created some charts that illustrate the point in a different way. Have a look at this chart, which shows pledge percentage rates for the 6th, 7th, 8th, 9th and 10th decile score, at four stages of call attempts:

This chart is based on data from more than 6,600 phone conversations. How are we to interpret it? Let’s start with the top line, in blue, which represents prospects in the top 10% (decile) of alumni for propensity to give by phone, as determined by the predictive model:

  • Almost 38% of 10th-decile alumni who were contacted on the very first call attempt made a pledge.
  • Moving to the next dot on the blue line, we see that almost 37% of the 10th-decile alumni who were contacted on the 2nd or 3rd attempt made a pledge.
  • The pledge rate slips a little more, to 36%, if the prospect picked up the phone on attempts 4 through 7.
  • And finally, almost 26% of them pledged if it took more than 7 attempts to reach them.

That’s the first line. The other lines take different paths. The 9s and 8s start much lower than the 10s, but pledge percentages actually rise with the number of call attempts. They will fall back to earth — just not yet! As for the lower deciles, the 7s and 6s, they start relatively low and dwindle to zero.

So what does all this tell me? I am less interested in how each decile ranks at the start of calling (one or two attempts), because it’s no surprise to me that the 10th decile gives at twice the rate as the 9th decile, and that pledge rates fall with each step down in the score. I’ve seen that before.

What really interests me is what happens when we’ve made many repeated attempts to call. That the 8s and 9s have pledge rates that increase with the number of call attempts is pretty strange stuff, but the fact is: 26 alumni with a score of 9 made a pledge only after we called them 8 or 9 or maybe 15 times.

Whether it’s worth it to make that many call attempts is up to you. It depends on contact rates, and what it costs to make all those calls. But one thing is certain: If I’m going to call repeatedly, I’d better be calling the top three deciles, because if I keep on flogging the segments with a score of 6, I’m not going to do very well.

So what about contact rates?

Here’s another chart that shows what percentage of each score decile’s prospects have been successfully reached at the same four levels of call attempts. (Click on chart for full size.)

What does it mean? Compare the lowest decile called so far (Decile 6) with the highest decile (10). About 14% of 6s answered the phone on the first try, compared with about 19% of the 10s. That’s not a big difference: In fact, contact rates are similar across the scores for the first attempt. But the similarity ends there. After the first attempt, the lower scoring alumni have steadily decreasing rates of contact. The same is true of the higher-scoring alumni, but the difference is that some of them are still answering their phones on the 8th call. More than 4% of 10s were reached on the 8th call or greater.

The bottom line is, the propensity score is your biggest asset in setting appropriate call attempt limits. Yes, Renewal prospects are more likely to give than Acquisition prospects. But that’s not enough to go by. Are you going to call every last Renewal prospect before thinking about acquiring new donors? I wouldn’t recommend it — not if you care about long-term growth and not just this year’s totals. And because contact rates decline as attempts increase (regardless of score), you’re going to end up making a LOT of phone calls to find those gifts that will make up your goal.

My earlier post on the same subject is here. I am spending a lot of time on this, because I don’t see any of this being written about by the well-known experts in Phonathon fundraising. Why that is, I do not know.

1 Comment »

  1. Terrific insight Kevin. Thanks for sharing your analysis. Another reaffirmation that loyal donors are well….loyal! And we should return the loyalty with good stewardship and gratitude!

    Comment by Keith C. Kerber — 12 January 2011 @ 2:25 pm

RSS feed for comments on this post. TrackBack URI

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

Create a free website or blog at

%d bloggers like this: