Configure your risk factors that determine the overall risk scores.
The “Risk Factors” page is Algoreg backoffice tool for managing and assessing the customer risk using a graphical decision tree editor.
Example of a rule decision tree (Go!Risk)
This page provides a user-friendly and efficient way to create, edit, and analyze decision trees. The page includes five types of nodes also called components, each with their own unique features, inputs, and outputs.
These nodes or components can be connected by edges to create a decision tree that ultimately leads to a leaf node, which represents the risk level of the customer (high, medium, low).
💡 This documentation guide will walk you through the process of using the “Risk Factors” page, including an overview of the interface, detailed instructions on how to use each node, and tips on how to effectively utilize the decision tree analysis functionality.
In the context of the “Risk Factors” page, a flow refers to a series of connected nodes or components that are used to analyze and determine the risk level of a customer.
There are two types of flows: “Customer Flow” and “Customer Relations Flow.”
💡 It’s important to note that before adding a new risk factor, it’s necessary to first determine the appropriate flow type. This means that you’ll need to decide whether a “Customer Flow” or “Customer Relations Flow” would be more suitable to analyze the risk associated with the factor you’re considering.
There are five main types of components that can be used in the “Risk Factors Flows” (risk factors definitions):
enc_U2FsdGVkX18JiSmjyrQ4l7FUoQcihCQ/dHFB0uKZQ2FYWpbfJoY9QTgL4S0HLVVvAov8AP/ObPw6Rt4mwafcpbV1etEinyTGyI6cNKu+Bie0s4bxG+kuLSPfJsiFs+o6eZqwYooNssnQiwShRpt15VNtzNrHJKECSjl7XIH7RDKHr2CK4GOPjtMMhn+916VerB3/tkK8iBP/VUHdUUVet3wAMakksmXQf4dNgFwnGaw=_enc
enc_U2FsdGVkX1/H5NBKeeSjjlvSzxo+5vBq1Oa7IuCtdhb/guwl3VaoeZn4YLMYILtjzJ4G5aYcnmyzIb1CXugTJdregiWfLD6r/WDO0wnmMVM=_enc
Like the types of flow, we have two main start components:
A matrix node will compare a variable with a set of values, and output one of four values: “high”, “medium”, “low” or “undefined”.
The matrix node works on strings
, numbers
and booleans
.
It has the following options:
Option name | Description |
---|---|
variable | The variable to compare. |
matrix_id | The matrix to use. |
use_regex | If true, the matrix will use regex to match the variable. |
The comparison node will compare two variables, and output one of three values: “yes”, “no” or “undefined”.
The comparison node works on strings
, numbers
and booleans
.
It has the following options:
Option name | Description | Example |
---|---|---|
variables | The variables code (aggregated to a single value). It can also be a static arbitrary value. | payment_method.code |
comparator | One of the following values: = , != , > , >= , < , <= , regex . | regex |
value | An arbitrary value used for the final comparison. | /^FR.*$/ |
The formula node will compute a number result from multiple variables, compare it to a value and output one of three values: “yes”, “no” or “undefined”.
The formula node works on numbers
and booleans
. Booleans are converted to 0
or 1
.
It has the following options:
Option name | Description | Example |
---|---|---|
variables | A map of named variables. | converted_amount and 30d_average_amount |
formula | A formula using the variables, the formula must return a boolean value and use valid math function defined here. | (converted_amount - 30d_average_amount) / 30d_average_amount |
comparator | One of the following values: = , != , > , >= , < , <= . | > |
value | An arbitrary value used for the final comparison. | 1 |
enc_U2FsdGVkX1/2tS2u1lKKQzQeq6M2NXIuHwGX2ZKxnc7Gqf8geVVOwK1WPj+uKa+JO5Gu7QMVOFSI99JcogXmPFIa/fyiu3pAKiFrKFG6ODJwzFJn0+AVWAPGUq/zEZRX/J5L5ZSC1jw32zGo7FbEVv3kfbbOv+9v9UhRQyGNxDLHikDrdI6xjo0cVzivNZfH_enc
It is based on number custom fields and uses three inputs: an aggregator operator, a comparator operator, and a threshold amount.
Based on these three inputs, the component creates a condition and decide where to go using “yes” or “no” outputs.
Inputs:
Outputs:
The leaf component is the final component in a flow and marks the end of the decision tree. It is used to determine the risk level of a customer. The leaf component comes in three types: Low leaf, Medium leaf, and High leaf.
Inputs:
Outputs: N/A
Adding a component to a flow is a straightforward process that can be done using the bottom panel, which contains all the types of components. This panel provides an overview of all available components and allows you to easily select and add the component that you need to your flow. Once you’ve selected a component, you can then customize its inputs and outputs to suit the specific needs of the flow.
💡 It’s important to note that the outputs of each component can be connected to the input of another component, allowing for the creation of a decision tree that is made up of multiple branches.