By 2019, it’s estimated that global spending on media is expected to reach $2.1 trillion, according to the Harvard Business Review. But is all that money effective in producing improved ROI? Without knowing which channels are driving sales, or more specifically, which individual efforts are working, marketing spending is like a black box.
In today’s world of digital commerce, it is not uncommon for a transaction to involve as many as thirty marketing activities, or “touch points.” Yet, many marketers take a convenient shortcut and credit each sale to the last touchpoint before the sale.
To properly attribute the influence of all marketing activities, businesses need an enterprise-grade methodology capable of quantifying each touchpoint’s impact on the sale. Ultimately, proper marketing attribution overcomes four major problems:
- Cluster analysis often results in inaccurate targeting;
- Attributing sales to the last touchpoint is flawed;
- Separating the effects of multiple touchpoints is difficult; and
- Determining which ads reached a specific consumer.
Machine Learning And Mapping The Path To Purchase
For effective marketing attribution, marketers need to develop highly-accurate predictive models. Traditionally, data scientists built machine learning algorithms manually. This process can be frustratingly time-consuming, with some projects taking months to deliver. By the time the algorithm is ready, it may already be obsolete.
Marketing needs a faster, less manual way to build the algorithms. The answer is Automated Machine Learning (AML), a technology that automatically constructs algorithms from historical data, sometimes in as little as a few hours instead of days or months.
Marketing Attribution With AML
AML enables users of all skill levels — including marketers — to make better predictions faster. By automating many of the skills traditionally applied only by data scientists, AML provides the fastest path to success for users who understand the business and the data.
AML can help users create sophisticated marketing attribution models to perform complex “what-if” analyses that quantify the effectiveness of different kinds of marketing activities and different combinations of marketing touch points:
- To begin, you need to determine a baseline – the sales that would naturally occur without any marketing activity. You can use AML to analyze the impact on sales if you remove all the marketing touchpoints.
- Then, determine the difference between actual sales and the calculated baseline sales. The more effective your marketing activities, the more sales are boosted above this baseline.
- Finally, assign a contribution for each touchpoint. AML performs a variety of what-if calculations on the impact to sales if you remove one, or multiple, touch points.
By using historical touch points and outcomes, AML automatically finds patterns, creating a model that predicts sales depending upon the touch points that apply to each lead. Using the model, you can run several “what if” scenarios using different touch points to predict how different combinations of touch points impact sales.
Attribution creates a clear guide to show you which marketing programs are worth spending money on. With this information, you do more of what works and reduce or eliminate what doesn’t. Want to learn more? Download the report or watch the on-demand webinar.
Based in Singapore, Colin Priest is a Data Scientist & Director of Product Marketing for DataRobot. Colin built his first machine learning model for marketing more than 20 years ago, when he needed to predict how sales would react to changes in product placement and pricing versus competitors. Over his career, Colin has held several CEO and general management roles, where he has championed data science initiatives in financial services, healthcare, security, oil and gas, and government.
