Risk Detection
Summary¶
This Neuron is designed to help you classify users based on their risk level based on his email address, IP address, and phone number. The Risk Detection Neuron extracts valuable information from these data points and uses machine learning models to predict the likelihood of a user being safe, suspicious, or risky. By leveraging advanced algorithms, this Neuron provides accurate and reliable risk detection, helping businesses prevent financial losses and protect themselves from fraudulent or fake users.
The Neuron has 3 different services: Fraud Risk Email, Fraud Risk Phone and Fraud Risk IP. Each service classifies users into 3 categories: safe, suspicious, and risky.
Warning
This classification is based on different features extracted from the email, IP, and phone number using several services. It is essential to consider other factors and perform additional checks to confirm the user's risk level but this Neuron is a good starting point.
Say goodbye to uncertainty in user risk detection. Embrace the power of Dedomena's Risk Detection Neuron and make informed decisions with confidence.
Use Cases
Here are some key use cases for the Risk Detection Neuron:
- Financial Security: Protecting businesses and individuals from fraudulent users, ensuring the safety of their financial transactions.
- E-commerce: Identifying potential fraudulent users in advance, allowing for proactive measures to prevent financial losses.
- Account Creation: Classifying the risk level of a user when they sign up for a new account, detecting high-risk users who may attempt identity theft using suspicious phone numbers or emails.
- Login Security: Analyzing user login attempts and mark users with risky IP addresses or emails, prompting multi-factor authentication for suspicious logins.
- Subscription Services: Detecting fake users who use disposable phone numbers or emails to sign up for free trials, preventing revenue loss from fraudulent accounts.
- Online Voting Systems: Classifying voters preventing tampering or vote manipulation by flagging IP addresses or emails commonly associated with bot activity.
- Spam Detection: Identifying suspicious emails or phone numbers used for spamming or phishing, protecting users from unwanted messages and potential scams.
- Payment Processing: Detecting risky users during payment transactions to prevent chargebacks or unauthorized payments.
API & Endpoints¶
Access API User Interface (Swagger) (1)
/v1/email¶
POST v1/email
This endpoint classifies email addresses into 3 categories: safe, suspicious, and risky. It also returns other features extracted from the email address.
Headers:
token: available via free trial or subscription.
Request Body:
It should be a JSON with the following field:
email_addresses(list): List of email addresses to classify.
Request Body - JSON¶
{
"email_addresses": [
"info@google.com",
"newuser@gmail.com",
]
}
Response¶
200
{
"info@google.com": {
"risk_level": "safe",
"valid_email": true,
"disposable_email": false,
"deliverability": "high"
},
"newuser@gmail.com": {
"risk_level": "risky",
"valid_email": false,
"disposable_email": false,
"deliverability": "low"
}
}
Description:
The response will contain, for each email address the next fields:
risk_level(str): The risk level of the email address.valid_email(bool): Whether the email address is valid or not.disposable_email(bool): Whether the email address is disposable or not.deliverability(str): The deliverability of the email address.
401
[
{
"detail": "Could not validate credentials"
}
]
422
[
{
"detail": "Unprocessable Entity"
}
]
429
[
{
"detail": "The maximum monthly number of calls or predictions for your account has been exceeded"
}
]
/v1/email/csv¶
POST v1/email/csv
In this case, the endpoint receives a CSV file with a column named email containing the email addresses to classify and like the previous endpoint, it classifies email addresses into 3 categories: safe, suspicious, and risky. It also returns other features extracted from the email address.
Headers:
token: available via free trial or subscription.
Request Body:
It should be a CSV file with a single column named email containing the email addresses to classify.
Response¶
200
{
"hello@email.com": {
"risk_level": "safe",
"valid_email": true,
"disposable_email": false,
"deliverability": "high"
},
}
Description:
The response will contain, for each email address the next fields:
risk_level(str): The risk level of the email address.valid_email(bool): Whether the email address is valid or not.disposable_email(bool): Whether the email address is disposable or not.deliverability(str): The deliverability of the email address.
401
[
{
"detail": "Could not validate credentials"
}
]
422
[
{
"detail": "Unprocessable Entity"
}
]
429
[
{
"detail": "The maximum monthly number of calls or predictions for your account has been exceeded"
}
]
/v1/phone¶
POST v1/phone
This endpoint classifies phone numbers into 3 categories: safe, suspicious, and risky. It also returns other features extracted from the phone number.
Headers:
token: available via free trial or subscription.
Request Body:
It should be a JSON with the following field:
phone_numbers(list): List of phone numbers to classify.
Request Body - JSON¶
{
"phone_numbers": [
"+1234567890",
"+9876543210",
]
}
Response¶
200
{
"+1234567890": {
"risk_validation": "safe",
"valid_phone": true,
"active": true,
"prepaid": false
},
"+9876543210": {
"risk_validation": "risky",
"valid_phone": false,
"active": false,
"prepaid": true
}
}
Description:
The response will contain, for each phone number the next fields:
risk_validation(str): The risk level of the phone number.valid_phone(bool): Whether the phone number is valid or not.active(bool): Whether the phone number is active or not.prepaid(bool): Whether the phone number is prepaid or not.
401
[
{
"detail": "Could not validate credentials"
}
]
422
[
{
"detail": "Unprocessable Entity"
}
]
429
[
{
"detail": "The maximum monthly number of calls or predictions for your account has been exceeded"
}
]
/v1/ip¶
POST v1/ip
This endpoint classifies IP addresses into 3 categories: safe, suspicious, and risky.
Headers:
token: available via free trial or subscription.
Request Body:
It should be a JSON with the following field:
ip_addresses(list): List of IP addresses to classify.
Request Body - JSON¶
{
"ip_addresses": [
"127.0.0.1",
"198.95.64.12",
]
}
Response¶
200
{
"127.0.0.1": {
"risk_validation": "safe",
},
"198.95.64.12": {
"risk_validation": "risky",
}
}
Description:
The response will contain, for each IP address the next field:
risk_validation(str): The risk level of the IP address.
401
[
{
"detail": "Could not validate credentials"
}
]
422
[
{
"detail": "Unprocessable Entity"
}
]
429
[
{
"detail": "The maximum monthly number of calls or predictions for your account has been exceeded"
}
]
Metrics¶
This Neuron provides the following metrics: