The detailed recommendation view is displayed in a pop-up window and provides a more granular breakdown of the budget optimisation calculations behind each recommendation. It also includes information about the reliability of the model results and the factors influencing the confidence level assigned to the recommendation.
The detailed recommendation view can be accessed in two ways:
From the 'Detailed report', by clicking the dedicated button under the 'Recommendations' column.
From the 'Recommendations' tab, by clicking any recommendation card.
1. The Revenue/conversions return curve
The Revenue/Conversions Return Curve provides a visual representation of the Budget Optimiser modelling results.
The chart contains three types of data points:
1. Actual performance (blue dot): The blue dot represents the actual budget spend and the corresponding revenue or conversions recorded on the selected analysis date.
2. Optimal performance (green dot): The green dot represents the modelled optimal budget spend and the estimated revenue or conversions that could have been achieved on the selected analysis date.
3. Historical performance (grey dots): The grey dots represent historical budget spend and revenue or conversion data points from individual dates within the selected lookback window.
For example, in the screenshot above, the selected analysis date is 17 June 2026 and the lookback window is set to 30 days. Each grey dot therefore represents the actual budget spend and revenue or conversions recorded between 18 May 2026 and 17 June 2026.
Additional chart options can be accessed through the three-dot menu in the top right corner of the chart card.
Alongside export options, you can:
Show or hide lookback data points.
Configure lookback data visualisation through the 'Compare lookback days' option:
No comparison: This is the default option. No additional comparison layer is applied, and all lookback data points are displayed using the same colour.
Weekdays vs weekends: Lookback data points are displayed using different colours to distinguish weekday data from weekend data.
Older to newer: Lookback data points are displayed using a colour gradient that visualises the progression of data from the beginning of the lookback period to the end.
2. Confidence level
The Budget Optimiser uses confidence level to communicate how much trust can be placed in each campaign's recommended budget changes.
1. Overall confidence level: Summarises the overall reliability of a campaign's optimisation model. The overall confidence level comes from combining the individual confidence level indicators explained below.
2. Individual confidence indicators: These are the individual signals that contribute to the overall confidence level and help explain why confidence is classified as low, medium, or high. Every recommendation is assessed based on the indicators:
Quality of fit
Data sufficiency
Spend variation
Conversion volume
Together, these indicators help answer questions such as:
• Was there enough recent campaign activity?
• Did spend vary enough for the model to learn from it?
• Did historical data show a clear relationship between spend and results?
• Were there enough conversions to trust the estimated business value?
A high confidence level indicates that the model had strong supporting evidence and sufficient data to generate recommendations. A lower confidence level indicates that recommendations should be interpreted more cautiously, or that additional campaign data may be required before reliable optimisation can be performed.
More information about the individual confidence level indicators can be found in the dedicate article.