The ”Risk Factors” page is Algoreg backoffice tool for managing and assessing the customer risk using a graphical decision tree editor.

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.

Risk factors flow

Risk factors = Flow

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.”

  • A ”Customer Flow” starts with a customer component and all subsequent components in the flow are based on customer information. This type of flow is useful for analyzing the risk associated with customer fields.

  • A ”Customer Relations Flow” starts with a customer relations component and all subsequent components in the flow are based on customer relations information. This type of flow is useful for analyzing the risk associated with a customer based on his relatives information instead of himself.

💡 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.

Risk Factors components

There are five main types of components that can be used in the “Risk Factors Flows” (risk factors definitions):

Start components

The start components are the first components in a flow and mark the beginning of the decision tree, they are created automatically when a new flow is created.

They define the type of flow and cannot be deleted.

Like the types of flow, we have two main start components:

  • Customer Start Component: marks the beginning of a customer flow. Inputs: N/A Outputs:
    • Start

  • Customer Relatives Start Component: marks the beginning of a customer relations flow. Inputs:
    • Relations: Filter by type of relations: wife, husband, etc…
    • Risk factors: Filter by existing risk factors. Example: PEP
    • Minimum risk level: Minimum risk needed for the chosen risk factors (low, medium, high). Outputs:
    • Start

Boolean component

The boolean component is used to make binary decisions based on input condition. It checks a boolean custom field and uses the result of that check as a condition to redirect the risk decision properly using the outputs “no” and “yes”.

Inputs:

  • from
  • field: Boolean custom field (is_pep, is_sanction, etc..)

Outputs:

  • no: if the condition is false.
  • yes: if the condition is true

Matrix component

The matrix component is used to make decisions based on input values falling within a set of range (matrix).

The custom matrices contain values and their corresponding risk level (high, medium, and low) (ex: matrix countries that define a risk level by countries).

The component uses the value of the provided custom field as input, and compares it to the values in the matrix to determine the corresponding risk level. The flow is then redirected to the appropriate output (low, medium, or high) based on the result of the comparison.

Inputs:

  • from
  • field: text custom field (is_pep, is_sanction, etc..)
  • matrix*:* custom matrix

Outputs:

  • low: if “_field _ matrix”* returns low.
  • medium :* if “field * matrix” returns medium.
  • high :* if “field * matrix” returns high.

Threshold component

The threshold component is used to make decisions based on input values exceeding or falling below a set threshold.

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:

  • from
  • fields: number custom fields (transactions_amount, age, etc..) on wich the threshold will be applied.
  • aggregator operator: specify how the values of the custom fields will be combined, such as summing them together or taking the average.
  • comparator operator: specify how the combined value will be compared to the threshold, such as being greater than or less than.

Outputs:

  • no: if the threshold condition is false.
  • yes: if the threshold condition is true

Leaf component

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:

  • from

Outputs: N/A

Adding a component

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.