Marketing Mix Modeling Report

Time period: Jan 2, 2023 - Dec 29, 2025

Model fit

Model fit is a measure of how well your MMM fits the data used to train the model. The best model for causal inference may differ from the best fitting model, because causal inference models must also estimate the unobserved baseline.

Note: The baseline represents the expected revenue without any media execution. The shaded blue area represents the 90% credible interval.

Model fit metrics

Dataset	R-squared	MAPE	wMAPE
All Data	0.99	2%	2%

Note: R-squared measures the amount of variation in the data that is explained by the model. The closer it is to 1, the better the model fit. MAPE measures the mean absolute percentage difference between the expected and the actual. The closer it is to 0, the better the model fit. wMAPE is MAPE weighted by the actual revenue.

Channel contribution

Your channel contributions help you understand what drove your revenue. Meta_Convert and Google_Convert drove the most overall revenue.

Note: This graphic encompasses all of your revenue drivers, but breaks down your marketing revenue by the baseline and all channels.

Note: Return on investment is calculated by dividing the revenue attributed to a channel by marketing costs.

Note: This is a percentage breakdown of all your revenue.

Note: This chart shows the estimated incremental revenue attributed to each channel and the baseline over the selected time period. It helps visualize how contributions have changed.

Note: This chart shows the relative rank of each channel's contribution, including the baseline, based on incremental revenue at the end of each quarter. Rank 1 represents the highest contribution.

Return on investment

Your return on investment (ROI) helps you understand how your marketing activities impacted your business objectives. Google_Convert drove the highest ROI at 2.4. For every $1 you spent on Google_Convert, you saw $2.39 in revenue. Meta_Convert had the highest effectiveness, which is your incremental outcome per media unit. Google_Convert had the highest marginal ROI at 1.23. Google_Convert drove the lowest CPIK at $20.54. For every KPI unit, you spent $20.54.

Note: Effectiveness measures the incremental outcome generated per impression. A low ROI does not necessarily imply low media effectiveness; it may result from high media cost, as positioned in the upper-left corner of the chart. Conversely, a high ROI can coexist with low media effectiveness and low media costs, as indicated in the bottom-right corner of the chart. The diagonal section of the chart suggests that the ROI is primarily influenced by media effectiveness. The size of the bubbles represents the scale of the media spend.

Note: Marginal ROI measures the additional return generated for every additional dollar spent. It's an indicator of efficiency of additional spend. Channels with a high ROI but a low marginal ROI are likely in the saturation phase, where the initial investments have paid off, but additional investment does not bring in as much return. Conversely, channels that have a high ROI and a high marginal ROI perform well and continue to yield high returns with additional spending. The size of the bubbles represents the scale of the media spend.

Note: CPIK (cost per incremental KPI) point estimate is determined by the posterior median, whereas ROI point estimate is determined by the posterior mean.

Response curves

Your response curves depict the relationship between marketing spend and the resulting incremental revenue.

Note: The response curves are constructed based on the historical flighting pattern and present the cumulative incremental revenue from the total media spend over the selected time period.