📝 Reporter
In the Reporter tab, the reports available for you to run are similar to what you have seen in the Insights tab (such as Waterfall Summary, Intercept Summary etc) however, you can make your own customizations to the input parameters.
Waterfall summary
This report shows the same information as the weekly snapshot view in the Insights tab. It contains four graphs.
Waterfall Graph
This shows a channel level breakdown of your KPI in a specified time period. The breakdown will show you how much each marketing channel contributed to your KPI in the time frame you determine.
Marketing Effectiveness
This graph shows the per channel ROI and MROI for the reporting period.
Spend
You can also see your spend broken down by channel for the reporting period to learn how much of your total spend went to each channel.
Share of Spend vs Share of Effect
This graph shows the spend and return for each of your channels. Hover over the Effect bar to see how much of the total spend was spent on a particular channel. Hover over the Spend bar to see the % of spend was earned i- return.
This report also contains a table with the per channel impact and spend for the reporting period.
To learn more about each of these graphs visit Weekly Snapshot in the Insights section
Intercept summary
The intercept summary shows the non-marketing (organic or “base sales”) portion of your business in a specified time period. That is, how many sales would you have in the absence of any marketing activity (or at least the marketing activity included in your Recast model). You can choose whether to include spike effects (holidays, promotions, etc) or not. This report can be run into the future to see the changes in the forecasted intercept.
The graphs in this report are line graphs showing the monthly and weekly changes in the intercept throughout your reporting period. Hover over the line to view the mean, median and range of the intercept during a particular week or month.
This report also contains a summary plot showing the daily intercept value every 7 days in the reporting period.
Shift curves
The shift curve report shows the estimated time it takes between when marketing activity happens in a channel (generally when money is spent) and when the effect of that activity is realized (e.g., in terms of conversions or revenue), for any channels you specify. You may specify which channels you want to run the report for.
The day when marketing activity takes place is day 0
Spend response curves
The spend response curve report lets you see the expected return at various levels of spend in the form of impact, ROI/CPA, and MROI/MCPA. You can specify a previous or future date to understand (for example) how a major shopping holiday like Black Friday may affect the total impact of your spend. To use, select which date you’d like to calculate this for and the channel you would like to include. Recast forecasts these curves 730 days into the future from the last modeled date.
Use your cursor to hover over the graph to see how much direct impact each of your channels contributed at the given level of spend as well the aggregate impact at that spend level at the top of the hover over box.
Channel performance
In this report, you can view performance over a specified amount of time, outside of the last twelve months view in the channel performance tab in the Insights dashboard.
What inputs are needed for the report?
The inputs needed are start date and end date for the reporting period. You can also select individual channels, aggregate channels or view all channels configured in the model within this report. You also can select to include lower funnel effects. Including lower funnel effects shows the full effect of the upper funnel spend by estimating the amount and performance of lower funnel spend and adjusting the ROI to reflect that contribution. To estimate only the direct effects of a channel, do not include lower funnel effects.
Fixed spend performance
The fixed spend performance report estimates the performance of a channel at a certain level of spend. The performance for the selected channel can be estimated for up to 730 days into the future, or in the past.
What inputs are needed for the report?
You can run the report for multiple channels or for a specific channel. The only other input needed to run the report is the amount of spend for the channel, or for the channels you want to review. We generally find it useful to input a small level of spend for the channel you want to review, in order to see the baseline efficacy before any saturation takes place (e.g. $1).
What can you review when the report is run?
When looking at the plot, you can review by multi channel or individual channel, as well as by impact, as well as ROI and MROI or CPA MCPA, depending on your model KPI.
Spend summary
The spend summary summarizes how much money was spent in each marketing channel in your model over a given time period. This report can be useful to compare the Recast model to internal systems. The time period for which the report is available will be shown in the dashboard.
What inputs are needed for the report?
- Date range
- Monthly or weekly view selection
This report contains two graphs. The first shows the weekly or monthly spend and KPI. Use this graph to find patterns in spend and your KPI. The second graph shows the total spend each week or month broken down by the amount spent in each channel. This graph shows both the blended and paid ROI over the reporting period.
Spike detail summary
The spike detail summary shows how different spikes (promotions, holidays, etc) affect your KPI on a day-to-day basis. It can be helpful in seeing the pull-forward and pull-back effect of promotional events.
This report contains both individual and grouped views of your spikes. Grouped spikes group each instance of a promotion eg. Black Friday 2022 and 2023 and is measured by the impact on your KPI in number of days from the spike center.
Period summary
The period summary provides a comprehensive report of a specified time period. It shows how much of your KPI was driven by spend in the time period vs. spend prior the time period. It also estimates how your future returns will be influenced by spend in the time period.
What inputs are needed for the report?
The only inputs needed for this report is setting the start date and end date for the reporting period.
What can you review when the report is run?
When run, you can review marketing spend in the time period. This is broken down by total KPI expected in the future from marketing spend in this period, KPI obtained after the date of report ran and the KPI obtained during the period.
Lower funnel details
The lower funnel details report shows the rate at which upper funnel channels drove spend into your lower funnel channels. For each of your lower funnel channels, the graph in this report shows a waterfall breakdown of how much spend each of your upper funnel channels drove into that lower funnel channel. Hover over the chart to see the % of total spend in the lower funnel channel driven by each upper funnel channel.
The report also contains a table with each of the upper funnel channels and the spend each of them drove in your lower funnel as well as the rate at which upper funnel channels drove spend into your lower funnel.
To learn more about lower funnel channels visit Lower Funnel Channels
Upper funnel details
The upper funnel details report shows how your selected upper funnel channel drives ROI to lower funnel channels. It compares the direct effect of the upper funnel channel with the total effect across time to show how much of the total ROI was from upper funnel channels directly and how much was from lower funnel channels.To use, select the time period for which to view the report and the channels you want to include.
For each channel selected, the report contains a graph of the Total ROI and the Direct ROI so you can see the proportion of Total ROI that is directly driven by your upper funnel channel over the reporting period. The difference between Total ROI and Direct ROI is the Indirect ROI from lower funnel channels at each point during the reporting period.
This report also contains a table of the lower funnel channels along with the per channel ROI and spend driven by each channel.
Questions this report can answer
Q. How much of my total channel ROI is driven by lower funnel channels at various points during the reporting period?
A. The difference between the Total ROI and the Direct ROI is the Indirect ROI. The indirect ROI is the measure of how much of your Total ROI is driven by your lower funnel channel
Q. How has the proportion of Total ROI driven by direct ROI from upper funnel channels changed over time?
A. Look at the change in the gap between the Total ROI and the Direct ROI to see the changing proportion over time.
Q. Which upper funnel channels drive the most spend into my lower funnel channels?
A. If the difference between your Total ROI and the Direct ROI is large, this upper funnel channel drives a lot of spend and ROI in your lower funnel
Context summary
The Context Summary report is a useful tool for companies who have models with additional factors affecting their marketing outcomes. For example, if you find that after a price change or new offer, your sales are performing differently, our new model will be able to measure these changes. The context summary report is where you can see the effects of these contextual variables on your sales and marketing spend.
This report is only included in some models where contextual variables impact the target outcome
To use the Context Summary Report:
- Navigate to the Reporter page
- Select “Context Summary” as the report type and input the date range for which you want the report to run
- The resulting report gives information on the Effect of Contextual Metrics, the Variable over Time and the Effect over Time
Contextual variables must be pre-configured in your Recast model before the report will be available
Interpreting the Graphs
The first graph in this report is the Effect of Contextual Metrics graph. This allows you to compare the % change in your marketing effectiveness and organic effectiveness as a result of changes in your contextual variables.
The next graph is the variable over time graph. This shows the change in the contextual variable we are measuring over time. In the graph below, we can see that the contextual variable was a one time price increase and a one time decrease.
The final graph is the effect over time graph. This shows the relative change in the marketing and organic effectiveness.
- When the price was low, marketing and organic effectiveness was ~9% better than now
- When price was high, marketing and organic effectiveness was ~4% lower than it is now.”
In-sample model fit
What is this report for?
This report shows the in-sample error of the model, and how well the model is fitting to the data that it observes. When run, you also receive more detailed stats, and can download these as a summary from the report. This can be used for evaluating the model’s fit to data it has been trained on for diagnostic purposes.
This can then be contrasted to out of sample testing, shown in the backtest tab in the Insights dashboard, where the model’s forecast is evaluated on how well it can predict performance from data it has not been trained on.
What inputs are needed for the report?
All that is needed is the start date and send date of the reporting period to run this report.
What can you review when the report is run?
You can review the predicted in-sample model fit vs the actuals. You also receive more detailed stats, and can download these as a summary from the report.
Marketing vs Intercept
What is this report for?
This report enables you to review the share of your total KPI driven by your marketing efforts vs how much is driven by organic sales. It shows your total KPI, the amount of KPI driven by organic and the amount driven by organic over time. This can be useful to identify business trends, seasonality, and helps answer the question, ‘how much does my marketing impact my KPI and how much does my intercept contribute to my modeled KPI?’.
What inputs are needed for the report?
All that is needed to run this report is date parameters.
What can you review when the report is run?
For the parameters run, you can review the contribution of both the intercept and the marketing impact to your KPI.
Variance Decomposition Report
This report produces two charts and is intended as a diagnostic tool for understanding why there may be a wider confidence interval for a channel. This may be due to lack of spend, or correlation with another channel, spikes or the intercept.
- A scatter plot of lack of signal against total spend. This enables us to decompose the question of where variation is coming from - either correlation with other channels vs low spend.
- A waterfall chart that decomposes the uncertainty in impact in a given channel to two sources (either correlation with other channels e.g. the intercept or lack of signal). The bars are sorted in decreasing order of spend into those channels, and the percentage represents the proportion of the model's uncertainty around the channel read that is brought about by the item in the bar. Lack of Signal is a significant contributor whenever spend in the channel is small.
Daily Spend vs KPI
This report enables you to compare spend patterns over time, and review your marketing spend against your modeled KPI. This helps to see the trend of your marketing spend vs how your modeled KPI is performing.
You can also run this report as a diagnostic tool, in order to identify correlations between your channels configured in the model.
We would therefore recommend running this report to better understand the patterns the model is seeing in the data, or to identify pairs of channels that are highly correlated in order to prioritize testing.
What inputs are needed for the report?
You select to review specific channels in your model, or multiple channels. The only other input is inputting the date parameters.
What can you review when the report is run?
When run, you can review both spend vs KPI and spend vs KPI scaled. You can also review correlations across channels.
Automatic Reports
When you are creating a new report, you can select to automatically update the report every time the model updates.
Step 1: Navigate to the Reporter
Step 2: Select your report type
Step 3: Fill in the information required for the report type.
Step 4: Select the checkbox next to “Auto-run on model update?”
To see your automatic reports, click the check box next to "Show only auto-run" in the report library. Automatic reports will be marked with the ♻️ symbol for easy identification.
What happens to the selected date range?
Every time your model refreshes, the reporting time period will shift relative to the model date. This means if the new model date is n days in the future compared to the date of the last model refresh, then all report dates will be shifted by n days. The next time the model is refreshed, all the report dates will be shifted by the number of days between the last model refresh and the latest model refresh.
You can use this feature to set up reports that will automatically generate for a given time period so every time the model updates, you can log into your dashboard and view the latest numbers in your report.
Updated 1 day ago