A Data-Driven Approach to Multi-channel Online Marketing

Our client, a globally operating digital marketing agency, develops advertising strategies and executes online marketing campaigns for its customers from a broad range of sectors. Their challenge was to determine the best possible allocation of marketing funds among multiple online channels, optimizing the overall effectiveness and return of investment of its marketing campaigns.

Each of the online channels, from search engines to video-sharing and social platforms, provided analytics data in different formats and at different time intervals. In order to implement a data-driven solution that spans all channels, Wolfram Consulting Group’s first task was to build a fully automated data acquisition pipeline and normalize the available information into a representation suitable for computation.

Then, using a multivariate time-series forecasting algorithm tailored for the kind of data our client provided from their previous campaigns, we developed and tested a tool that could accurately and reliably predict the evolution of the outcomes of the different channels. During the course of an ongoing campaign, this tool was used to propose reallocation of spending over different channels so our client could dynamically optimize the overall return on investment.

Finally, we extended the algorithm so that our client could either calculate the budget necessary to achieve a chosen outcome KPI or, alternatively, forecast the outcome for a given budget.

The solution was delivered to our client with an easy-to-use graphical user interface to explore “what-if” questions and visualize a wide range of scenarios. Our solution attracted new clients who were seeking cutting-edge approaches to managing their digital campaigns.