Hidden online customer journey: How unseen activities affect media mix modelling and multichannel attribution

Abstract

The purpose of this article is to verify the impact of missing the earned media and category media in multichannel conversion attribution models on digital media budget allocation. The analysis is based on a very unique approach: 532 users who declared their will to purchase a selected product in the next 3–5 months agreed to install special addons on all their devices connected to the Internet. These devices will register all the users’ activities throughout three months. All user activities on the path to purchase were extracted by means of text mining (URL analysis) techniques. Finally, 5171 activities were found and assigned to particular media areas and media channels. The average user spends 20 per cent of his time in the paid media and owned media areas. However, from the point of view of the number of touchpoints, 29 per cent of the activities occur in these two areas. The obtained results clearly show how much of consumers’ activity in the decision-making process is beyond the control of marketers who, on the basis of this partial data, have to make daily decisions about allocating advertising budgets. The study compared the results of conversion attribution for the full funnel (paid media, owned media, earned media, category media) with the conversion attribution based only on paid media and owned media. The results indicate that not all attribution models lead to similar conclusions in both approaches.