The Uses of the Half Life Day
by Arthur Middleton Hughes

 

When you send out a promotion or a catalog, the phone calls resulting in your responses and sales typically arrive over a considerable period of time. Unless you have given your prospects a definite deadline, the sales can stretch over several months. This is seldom a problem for the marketer, with one exception. If the promotion is a test, you don’t like to wait for months until you know if your test is a success. For example, suppose you are trying to decide whether to price your product at $69.95 or $89.95. You might think that it would sell better at the lower price, but experienced marketers know that that may not be the case. Depending on your audience and the product involved, the higher price may make the product seem more substantial, and could result in higher sales. And, of course, higher unit volume means much more revenue at the higher price.

Suppose you have a prospect list of a million names ready to go. You have sent out two identical offers of 50,000 each to an A/B split test of identical households testing the two prices. If it takes five months before your sales are complete, the waiting can be quite costly to you. You need to know now – not five months from now – which offer is the most profitable for you. This is where the half-life concept comes in.

Experienced marketers have learned that for every product situation, there is a magical half-life day on which half of the orders have been received. For example, if you are going to get two thousand orders over five months, there is one day, in those five months, in which the one thousandth order was received. Typically, that day occurs in the first month, or slightly later. The second thousand orders are strung out over the next four months. Marketing experience shows that this day is often common to all promotions made by the same company to a similar audience.

For example, by tracking sales in the past, Sears Canada learned that their half-life was 20 days after a catalog was mailed. That means that after twenty days, they have received half of the orders that they are going to get from that particular catalog. They can track the entire success of a book by sales made during the first 20 days. This is powerful knowledge.

The power comes from the fact that you can conduct extremely rapid tests. In the example given above, if the marketer knew his half-life day, he could know after three or four weeks which offer was the most profitable, and could launch his million household rollout months earlier. Time is money, and half-life saves time.

At the Database Marketing Institute half-life theory has been taught for some time. Institute staff has have worked with some participating companies to discover how it works in their situations. Half-life computation is often tedious work. For this reason, the Institute developed added a half-life computation model which it added to its standard RFM software. They applied this module to some of the participant’s promotion responses with interesting results.

Here are the results of half-life analysis of a company that sent out a product catalog on July 15th 1997. They sent out 45,000 pieces, and after waiting 197 days, had received 1,804 orders totaling $133,986 by the time the campaign ended. The RFM software developed by the Database Marketing Institute was used to graph their response.

Looked at day by day, the responses do not show much of a pattern. They tended to come in heavy at first and then peter off later in the year. A better look at the responses is to see their cumulative effect:

But, the most useful picture comes from numbers.

Days Responses
Total 197 1804
Half Life 35 904
Third 18 616
Quarter 13 498

In just 35 days the cataloger had received half of all the responses they were going to get. It took five and a half months for the remainder to straggle in. The dollar receipts had almost the same pattern:

Days Revenue
Total 197 $133,986.00
Half Life 35 $67,007.17
Third 15 $45,643.97
Quarter 12 $33,557.45

Half of the dollars also arrived in the first 35 days. This company sends out a catalog six times a year. They test different lists, offers, and formats. Before they discovered half life, it took forever for them to come to a conclusion as to whether their campaigns were going to be successful or not. Now, they can just wait 35 days, and multiply the results by two. They are beginning to experiment with third life day, which gives them results in only 15 days. Time will tell whether this will prove as accurate as their half life does.

Half-life is not a major breakthrough like lifetime value, profitability, or RFM. It is just a small step. But it does give a marketer the ability to conduct many more profitable tests than he could without it. When used intelligently, it can boost profits.

 


Arthur Middleton Hughes is Vice President of The Database Marketing Institute. Ltd. (Arthur.hughes@dbmarketing.com) which provides strategic advice on relationship marketing. Arthur is also Senior Strategist at e-Dialog.com (ahughes@e-Dialog.com) which provides precision e-mail marketing services for major corporations worldwide. Arthur is the author of Strategic Database Marketing 3rd ed. (McGraw Hill 2006). You may reach Arthur at (954) 767-4558 .


The articles on this web site are available to the general public to read, enjoy and for limited business use. If you want to reprint more than one or two of them for resale or use in a business or educational environment, send an email to Arthur Hughes at arthur.hughes@dbmarketing.com. He will give you permission by return email. The cost, depending on the number of copies you want to reprint, is very inexpensive.