...
The integration with Kount API enables Thiio to analyze multiple data points, including device information, IP addresses, geolocation, transaction history, and other relevant data, to assess the legitimacy of each transaction. This comprehensive approach significantly reduces the likelihood of fraudulent activities slipping through the system undetected.
Fetch API Keys
Access Kount’s Dashboard: Once your account is created and verified, log in to your Kount account and navigate to the ADMIN section on the top right menu. This is where you can manage your API keys and access other related resources.
Click on API Keys link.
Generate API Keys: Once in the API Keys section. Click on the Create API Key button.
A new form will pop up where we’re required to enter a name for the new API Key and it is important to check both options RIS and API.
Click on Create API Key; a new API Key will be rendered.
Fetch Website
From the Kount’s dashboard click on Fraud Control button on the top right menu.
Select Websites from the menu.
Once in this section if no website has been previously created, it is important to add a new one.
When the new form is shown fill the name of the website, add a small description and check on the ENS Enabled the Yes option.
Leave the ENS URL empty.
Click on the Add Website.
We’ll use this information when setting up the integration on Thiio’s admin later.
Create Submerchant ID as UDF
When using the same Kount account across different platforms it is convenient to have a way to differentiate them from each other. Kount provides User Defined Fields (USD) that can help us with this problem. In order to create a submerchant ID we need to follow the following steps:
...
After these steps whenever a request is sent by Thiio to the API, this field will be present and it will be easier to identify which account is being used for validating transactions.
Kount RIS configuration file
As part of the onboarding process when opening a new Kount account, it's worth noting that the customer support team is known to provide a Kount RIS PHP SDK Configuration file. This configuration file is a crucial component for integrating the Kount RIS (Risk Inquiry System) PHP SDK into your application.
...
MerchantID
Config Key
RIS Endpoint URL
Data Collector URL
Set up Kount
On thiio’s admin it is important to access to the integrations section from the menu on the left.
Then click on the add (+) button in order to open the catalog of integrations.
Search for the Kount integration.
On this form we’ll fill it out with the Website we created on the Fetch Website section above. The URL is the same url as the RIS Endpoint URL provided by Kount’s Customer Support team.
The data collector URL provided by Kount’s customer support team.
The key is the API Key we created on the Fetch API Keys section described above.
Merchant ID is the same provided by Kount’s Customer Support team.
And the Submerchant ID we got it from the Create Submerchant ID as UDF section above.
Persona Score & Omniscore
In the context of Kount, a persona refers to a profile or representation of an individual or entity engaging in an online transaction. It is a dynamic and data-driven identity that helps assess the risk associated with a particular user or transaction. Kount assigns a persona to each user based on various data points, behavioral patterns, and historical information.
...
Both the persona and Omniscore are integral components of Kount's comprehensive fraud detection and prevention system. By leveraging these tools, businesses can assess the risk associated with each transaction and take appropriate actions to protect themselves and their customers from potential fraud.
Persona Score & Omniscore
| Info |
|---|
It is important to define a threshold for the Omniscore and the Persona Score. Thiio allows to work with them individually, meaning that we could evaluate transactions only using either Omniscore, Persona Score or both at the same time. For more reference about what these values mean please review the information below gathered from Kount’s official website. |
...
Persona Technology and Persona Score Usage
5 months ago
Updated
FollowNot yet followed by anyone
Persona Technology is a real-time unsupervised machine learning algorithm that identifies direct and indirect linkages between transactions. It is designed to detect emerging fraud across Kount’s vast network of online businesses and their transactions. The Persona Score is a measure of the transaction risk generated by Persona Technology.
Identifying a Persona
A Persona is a set of transactions linked by common attributes. Persona is not a static medium; but rather they are created and updated in real-time as transactions are submitted to Kount. Persona Technology is optimized to filter outdated transactions to ensure that a Persona represents current activity limited to the last 14 days.
Calculating Persona Score
In real-time, Kount derives over 200 data elements from a Persona that provide insight into the risk of a transaction. The score is calculated by analyzing these data elements via a proprietary mathematical algorithm. Some of the data elements that can impact the value of the score are as follows:
...
The score indicates the risk level for a given transaction based on data linked to other transactions. It ranges from 1-99, with 99 being the riskiest.
Interpreting Persona Score
Transaction risk is the inverse of transaction safety. The Persona Score is a measure of transaction risk ranging from 0 (low risk) to 99 (high risk). Higher Persona Scores indicate higher risk.
...
Persona Score | Risk Level | Description |
0-40 | Low Risk | Small Persona, few if any risk factors |
41-70 | Medium Risk | Some risk factors present in Persona |
71-99 | High Risk | Large Persona and/or significant risk factors |
Omniscore Overview
7 months ago
Updated
FollowNot yet followed by anyone
...
Omniscore differs from previous scores in that it incorporates the most predictive components of both our supervised machine learning and our unsupervised machine learning, as well as other predictive factors, into one score.
The best of both worlds in one score
Omniscore uses two types of machine learning – unsupervised and supervised. The unsupervised machine learning focuses on short-term linkages and patterns, enabling it to catch emerging fraud attacks and anomalies that supervised machine learning cannot yet learn about due to the recentness of unseen attack types. Our supervised machine learning technology learns from historical data – decisioned orders and their outcomes.
The AI simulates how an experienced fraud analyst would review a transaction. The unsupervised machine learning aspect of Omniscore evaluates the transaction as a human would use instinct. The supervised machine learning aspect evaluates the transaction like the historical experience of seasoned fraud analysts. Together they allow Kount to calculate one highly-predictive transaction safety rating that can be relied upon for decisioning orders, so that there is less reliance on manual review and reactive fraud rules. The result is catching more true fraud and allowing more good transactions to generate revenue.
Interpreting Omniscore
Transaction safety is the inverse of transaction risk. Omniscore is an indicator of a transaction’s safety ranging from .1 (unsafe) to 99.9 (safe). A safe transaction will have a relatively high Omniscore and an unsafe transaction will have a relatively low Omniscore.
...
It is important to note that Omniscore is not a decision. It is a prediction of safety that is used by customers to decision a transaction (either automatically via creating a rule or manually while under review).
Low/High Omniscore anomaly
A Low/High Omniscore alert is generated when Kount has identified a decrease in high Omniscore ratings and/or an increase in low Omniscore ratings, on transactions within your merchant account. This means that increased indicators of risk were found, which can indicate a rise in fraudulent orders that may be worth investigating.
Creating a fraud rule with Omniscore
Since Omniscore is so accurate in predicting fraud, you can set one rule around it instead of creating large rulesets targeting fraud.
...