Do you have the propensity to make better decisions?

Propensity is a word we use a lot in marketing, and not much anywhere else. Marketers and brands want to predict what their customers will do next: do they have a propensity to lapse, a propensity to buy again, or a propensity to donate in the charity sector? Propensity models exist to try to predict these events.
But you don’t often hear people say they have a propensity to eat chocolate late at night (I do) or that their dog has a propensity to eat her food really quickly (mine does) or that their wife has a propensity to buy far too many shoes (…just an example, obviously).
So why does the word get so heavily used in marketing? It seems to sum up our need as marketers to try to predict what customers are likely to do next. When it comes to propensity, what we really mean is the tendency to do one thing more than any other. In marketing that means finding the people who are more likely to do the thing we want (or don’t want) them to do.
This comes down to probability – as do most things in life – and the likelihood of something happening. So, for example, if I buy chocolate on the way back to my hotel room when staying in London two nights out of three, the likelihood of me doing it the next time I am staying in London is two thirds. However, if the weather is hot next time I’m in London, I’m less likely to do so and you can decrease that likelihood.
But does my likelihood to buy chocolate late at night allow you to predict who else will do so? Only if you know that they are Scottish (and therefore a sugar addict) or that they crave chocolate after having a beer or that they believe that having a run the next morning justifies eating chocolate the night before. So, yes, certain predictions can be made, as long as we have the right data to understand the factors driving the decision.
Individual and group perspectives
There are two ways to look at this. Firstly, at an individual level (‘What is the likelihood that I will buy some chocolate tonight?’) and secondly, from a group perspective (‘Of all of the people we are interested in, who will buy chocolate later tonight?’). Being able to work this out could help sell more chocolate (or cut down diabetes if we use the data wisely).
You can apply this same way of thinking to selling a product, asking for a donation, renewing an insurance product or taking a holiday. The key is to find the people with the propensity to do each of these things.
From an individual point of view, it will really help us as a company if we can work out what each person wants to do next with us based on what they and others have done in the past. By using the ‘next best action’we look across all of the different options and pick the one we think is most likely. To do that accurately, we must take into account past behaviour, current status (what they last bought, when and how much they paid), the behaviour of lookalike customers, along with what we want to sell to them, to ensure we make some money too.
By balancing all of these things we can create a model for each person that scores all the likely events and picks the one most likely to happen, weighted if needed towards where we make profit. We can then suggest this to the customer at the appropriate time to help inform their decision.
At the group level, it is very similar but with a slightly different outcome. Here we want to apply a score to everyone and pick those with the highest likelihood, probability or propensity to do that thing. For example, if we are looking for people to take part in a particular event, we want to ensure we pick those who are most likely to do it. We create a model that scores everyone and then pick those at the top who are more likely to do that event.
Data is key
Key to both of these approaches is data, along with having both the right data and enough data to allow us to build the models. Generally, that data will exist inside your business between the data you have on existing customers as well as past behaviour and outcomes (e.g. who lapsed when and why). External data can also help bring a different view of a consumer – what they do outside your business, online, on social media and beyond.
Making the decision to harness this data, apply it to our customers and the outcomes we are interested in can help us increase our propensity to make better decisions. And that’s what we all really want, isn’t it? It’s something I need to bear that in mind next time I’m walking back to my hotel after a few beers with a grumbling stomach.