It’s perhaps easier to say when they predict the same thing. This is usually when there is essentially no behaviour in the control group. For example, if a set of people purchase product X after a mailing, but no one purchases it without the mailing, and uplift model should predict the same thing as a conventional response model. Their predictions are most different when the variation in the change in behaviour opposite from the variation in the underlying behaviour.

For example, suppose the background purchase pattern (the one you see if you don’t do anything) is that mostly men by product X, but the effect of a marketing action is to make more women buy it, but fewer men, even though still more men than women buy when treated. In this case, uplift models will make radically different different predictions from “response” models.

A response model will concentrate on the fact that more men buy (when treated) that women; but an uplift model will recognize that women’s purchases are increased by the treatment whereas men’s is suppressed.

The fact is churn can be triggered by your active marketing campaign. Effectively your retention campaign can be having the opposite effect on some customers – they would have remained customers if you had left them alone. We rather descriptively call these customers ’sleeping dogs’ (from the saying let sleeping dogs lie) or – perhaps more politically correct – ‘do-not-disturbs’.

It’s a real phenomenon.

A mobile phone operator ran a retention mailing that increased churn from nine percent to ten percent. Imagine walking into your boss’ office to announce the expensive direct marketing campaign not only cost the company the campaign budget, it also drove recurring revenue out of the business.

As it turns out, just 30 percent of those targeted were ’savable’. Using Uplift Modelling this ’savable’ sub-segment was identifed for another retention campaign but with very different results – this time positive responses reduced churn to 7.8 percent across the retention segment.

The 1.2 percent churn saving was worth more that US$8 million per year.

The numbers tell a very convincing story – now just extrapolate this scenario onto the last direct marketing campaign you ran. What happened with your sleeping dogs?

So now that your boss and the Board demand that you talk the language of numbers, how are you going to make them really sit up, pay attention and throw budget at you? Yes that is a bit contradictory – GFC and gaining more budget – but if you can demonstrate your marketing ROI will be triple digits several times over, reducing budgets equates to limiting your own growth, so aim for more or at least to hold steady against last year.

It is possible to take the same campaign and improve response by over a third while not spending close to half your budget. The reason you save budget is you are no longer targetting everyone in your campaign as equals. There are those who will leave because you contacted them – your contact triggers a consideration of alternatives and attrition (read about Telenor and churn). There are those who aren’t impacted at all by your campaign – if they were to buy they would regardless; if they won’t buy they won’t be fishing out their wallet just because of your communication.

The focus, the core, the central ethos for your campaign is to only communicate to those for whom the contact triggers them to take a desired action – without the campaign they would not react. The campaign directly causes a response so every dollar spent is returning incremental revenue.

But just as Wanamaker found in the early days of advertising, it can be difficult to determine who will be persuaded by your campaign and who it will be wasted on (waste in terms of no return). Well, it was until Uplift Modelling.

And for those who are under pressure to deliver greater marketing ROI right now, an uplifting insight using Campaign Checkup is free.

A small word of warning though, after your ‘wow’ moment you will quickly morph into asking questions like ‘but how?’ and ‘would it work for me?’ Rather than have you perplexed, we suggest that you gather your last campaign’s data (including from your control group and your per unit financial data) and complete a checkup on your campaign.

That way you can see exactly the potential budget savings and ROMI for your campaign based on your data. The form for the checkup is here.

Please feel free to browse the site, read the documents, listen to the webinars and comment on the blogs.