Skip to main content

Symon.AI help center

Payout Outliers

Abstract

Identify payout outliers to help you catch mistakes before sending out payments.

Identifying payout outliers can help you catch mistakes before sending out payments. This Blueprint flags outliers in your key payment variables. It also flags any commission payouts that you should review.

Legend

The tools in this Blueprint are color-coded based on their function:

  • Yellow: These tools contain the input data or results that are ready for export. These are what you’ll be mapping to in ICM for the Symon.AI Calc object. The Payout Data (Data) tool contains the incoming transaction data that you want to find outliers in.

  • Pink: These tools contain the core of the outlier analysis that this blueprint provides.

  • Red: The Outlier Type (Case) tool contains the business logic to combine the results of the outlier analysis.

  • Blue: These tools manipulate and transform data for visualizations.

  • Turquoise: These tools are used to manipulate data for import and exports.

  • Lime Green: These are the output tools which contain results that are ready for export.

Pipe inputs

This Blueprint uses the Adapt tool to map the columns in your data. This blueprint assumes that sellers receive credit for deals they're involved with. It also assumes their final commission is calculated based on the credited value at a rate defined by the compensation plan. For reference, these are the definitions we're using:

  1. Credit: The part of the sale credited to the seller in dollars.

  2. Rate: The rate used to calculate the final commission for the seller based on the credited value.

  3. Commission: The amount of commission paid to the seller.

You can look at the sample data to see how the tool maps columns. Whatever column names you use, you can use the Adapt tool to change them to names the pipe recognizes. In the sample, the remapping looks like this:

  • Commission to Commission (no change)

  • Rate to Rate (no change)

  • Credit_Value to Credit

How to interpret the results

The Export List of Outliers (Export) tool contains the payout outliers identified by Symon.AI. The other export tools power the visualizations. You should review any payouts flagged as outliers. To make that review easier, this Blueprint also lists a reason for the outlier in the Outlier_Type column.

Looking at the Outlier_Type column can help you identify problems in a compensation plan. For example, if the outlier type is a Commission Outlier, it means that the Commission payout amount was higher than normal. If a seller lands a large deal by themselves, you'd expect their Credit and Commission to both be high. But in this example, it's only the Commission that's high. That's why Symon.AI flagged this payout as an outlier.

Visualizations

This blueprint comes with visualizations and dashboards , no configuration required. Looking at these visualizations can help you identify next steps.

Payout and Outliers by Plan: This visualization shows the amount of outlier payouts by compensation plan. This will help you identify potential problems in your compensation plan design.

How it works

This Blueprint looks at the final commission payout value and the two most common factors used to calculate commission: the credited transaction amount and the rate multiplier. The Blueprint then analyzes each of these attributes using three different outlier tools. The Blueprint runs the results through business logic in the Outlier Type (Case) tool.

Tools labeled pink are where the blueprint analyzes the outliers. If you look for these tools, you'll find three: Commission Outlier - Z Score (Outlier) , Commission Outlier - PCA (Outlier) , and Commission Outlier - kNN (Outlier) . Each of these tools finds outliers in data sets with different distributions. For example, Commission Outlier - Z Score (Outlier) is great at finding outliers in normally-distributed data. It doesn't perform as well when the data is randomly distributed. That’s where the other tools come in, each tool can find outliers with different types of data distribution.

Once Symon.AI identifies an outlier, the business rules encoded in Outlier Type (Case) help reduce false positives. For example, if a seller's payout amount is higher than normal, it wouldn't show up as an outlier if their credited amount is also high.