The concept of the customer journey has gained attention not just because brands are competing on customer experience, but also because it’s a proven approach that delivers results: brands creating multi-layer journeys for their customers find a strong correlation with increased loyalty and sales.
So what is customer journey, and how can I get started?
The customer journey is the complete path which a customer takes when interacting with a brand, from the initial contact to final disengagement and is the sum of all the experiences a customer goes through. A touchpoint is simply a point of interaction along the journey and, much like a journey is when travelling, our experiences begin with how we arrive at the business in question. Whether by computer, mobile device, or even within an application platform, these various points of interaction serve as the touchpoints in our digital journey.
Your customers are interacting with you across many channels – from Twitter and Facebook to emails, apps, and your website. And with each interaction, you’re collecting valuable information about them, and building extensive customer profiles with preferences, purchase history, and even personal details like birthdays or anniversaries. By simply capturing your customer information, you’ve already done the heavy lifting. If you haven’t already, take the time to undergo a customer data audit and identify all of the places where your company is collecting and storing customer data. This data can provide vital insight as to when on your mapped-out journey it would be most effective to reach out to a particular customer and with what information.
The Importance of Analysis and Optimization
For optimizing digital marketing budget allocations it’s important to understand differences in the journeys and touchpoints of customers and non-buying users.
For example, assuming you knew, that 35% of all your buyer’s journeys included a click on a generic keyword campaign in Google Adwords. You might be curious to announce that this channel is a great indicator for predicting whether a journey will lead to a purchase (conversion). But what if 50% of all your non-buyers had this touchpoint as well, do you still think it’s a good indicator for a user buying?
Accurately measuring all user journeys is a challenge. The tracking solution needs to integrate all channel-clicks (and preferably -views), the ones from cookies that have converted at some point and the ones from cookies that haven’t. Such a system needs to include setting cookies and referrer analysis and combines purchase-data with channel-click data on a cookie-id, i.e user-id basis. It’s decisive for the quality of the attribution modelling to spend sufficient time validating the tracking implementation.
- Is every campaign and channel interaction being tracked?
- Are there interactions that are double-counted?
- Comparing the aggregated numbers with stats from Google Analytics or other web analytics tools is useful.
But from painful experience, I can only recommend to manually test as much as possible. This would include creating fake user journeys, for example by clicking on one’s own google ads, or bots. Then one should validate whether these actions have been tracked correctly as per timestamp.
For developing an attribution model, the conversion event is our binary target variable (customer bought or signed up). The variables about the channel interaction (e.g. the number of clicks on “paid search”) are the covariates that predict the value of the target variable.
This way the modelling problem becomes a regular classification problem. These include using training- and test-sets, cross-validation and a set of metrics for measuring model quality. Common metrics for evaluating the quality of predictive models with a binary target variable are AUC (area under the curve)
Since we aim at interpreting the model’s coefficient estimates as the effect of each channel interaction, we need to make sure that we have relatively robust estimators. This needs variable selection and eliminating multicollinearity. Once we have sufficient good and robust model in place, we can go ahead and “score” through every customer journey.
This customer journey started off with a display ad click, followed by a click on an affiliate site. The last-click right before the conversion was a paid search click. For every stage, we apply the model and calculate the probability that the customer converts. We assign the incremental change of conversion probability to the latest channel. So in the “Research & Compare” phase of this particular journey, the affiliate channel generated an increase in conversion probability of x%, so affiliate will be assigned x% of this conversion. This approach considers the previous channel interactions. It dynamically calculates channel effects individually per user journey instead of using the same channel weights overall user journeys.
Because of this process, we have the number of conversions and sums of revenues attributed to each channel.