The Marketing Mix Model dashboard is powered by a machine learning model, an algorithm that examines large amounts of historical data to find relationships between multiple variables. It can then use those relationships to make predictions about future performance.
Because it’s automated, the model can consume extremely large amounts of data very quickly and uncover patterns faster than an entire team of human analysts could.
The model does this by “training” itself — constantly updating and optimizing its understanding of the relationship between variables with each new piece of data it encounters.
Marketing Mix Model and Machine Learning
In the case of ChannelMix's Marketing Mix Model, we use a supervised learning model.
We provide the model with specific inputs (how much was spent on each marketing channel) and a specific output (leads, sales or revenue generated) and ask the model to find the rules or patterns that link those two sides.
For example, the model might reveal that …
- Spending $10,000 on Channel A leads to $100,000 in new revenue
- Spending $10,000 on Channel B generates $50,000 in new revenue
- Spending $10,000 on both channels at the same time creates $300,000 — a multiplier effect
And that’s just a tiny, tiny sliver of the patterns that might be uncovered by the model. The model can make predictions for multiple combinations of channels at multiple levels of spending.
Or put another way, you can use the model to make predictions. Alight’s Marketing Mix Modeling dashboard includes a calculator where you can run scenarios based on different channel mixes and levels of spend. Enter your numbers, press the button, and the calculator will show you what could occur, based on the model’s findings.
Machine learning models require large amounts of historical data in order for the model to train itself correctly — at least 18 months, in the case of our Marketing Mix Modeling dashboard.
Alight will regularly incorporate a client’s most recent media data into the model. Generally speaking, updates occur every two weeks.
As new data is added, the model will update and refine its predictions based on these new results.