Human Managed app hm.works 1.10 released with dashboard on detected fraudulent behaviors
Since its first release on 13 March 2023, the Human Managed web app hm.works has been getting fresh updates every single week to report on intel generated from any data source from our customers.
📝Note: Read more about our approach to creating intel on your digital business' assets, postures & behavior, and establishing 🔗relationships🔗 between them to improve your decisions and actions for many use cases.
This week, we are excited to announce the release of a dashboard that reports on the detections of possible fraud on our customer's digital services such as online banking application.
Introducing...
fraud dashboard 🎭
Our fraud dashboard reports on various fraud use cases that hm.works runs on the data generated by your services and products.
The hm.works platform analyzes logs, metrics, traces, alerts or events from multiple data sources (e.g. transaction systems, apps, APIs, security tools, and other contextual information like consumer data) to:
- detect events of interest that indicate potential fraud or suspicious behaviors for use cases such as Identity Obfuscation, High Money Transfer, Stolen Credit Card, Address Manipulation, Account Takeover, Identity Theft, Malicious Activity, or Anomalous Activity.
- discover previously unknown information to enrich events generated by your consumers and provide fraud intelligence feeds to detect use cases. For example, data points such as consumers' devices, browser version, cookie preferences, etc. can be used to identify suspicious users and bots before they perform a transaction on the service.
- profile behavior baselines from your consumers' historical interactions and transactions with your services over time. The profiles give context of what is 'normal' or 'expected' to enrich events and provide fraud intelligence feeds to detect use cases.
A single page answers the top 3 things you need to know about potential fraud or malicious activity so you can speed up response actions and take proactive measures:
- What fraudulent or suspicious behaviors are detected in my services and products?
- How do my consumers' behaviors deviate from their baselines over time?
- What are the fraud patterns observed in my services and products across multiple use cases that I should respond to?
What's fraud and why is it important?
Fraud is an intentionally deceptive action to get an illegal advantage or to harm the victim's rights, through false representation of information. Common examples of fraud include tax fraud, credit card fraud, securities fraud, corruption, etc.
In today's connected world, fraud involves the perpetrator using online services and software to defraud or take advantage of victims. Techniques involve identity theft, stolen card details, phishing across a supply chain of products and services to gain access to the ultimate objective.
As customers and users' interactions with your business is increasingly digital, it's important to know what to observe in your data, what is 'normal' vs. 'abnormal' behavior, and when to take action.
* * *
Let's explore each segment of the fraud dashboard.
Fraud Detection use cases over time
- What: This line chart reports the number of times subscribed fraud use cases have been detected by hm.works platform over time.
- 📝Note: hm.mworks platform uses automated detections consisting of pre-defined conditions, correlation rules and/or machine learning algorithms to identify suspicious or malicious activities and create Detections that need to be actioned.
- Why: Gives you improved fraud visibility across your environment of multiple services and products, so that you can respond faster to mitigate risk and reduce business impact.
- How: Forward data from your product or services (e.g. transaction system, applications, APIs, security tools, contextual information such as identity / asset / consumer data) to monitor and build fraud use cases on the hm.works platform.
Fraud Indicators
- What: This table lists all subscribed fraud use cases, the types of behavioral indicators that trigger the detection for each use case and the number of times the indicators are detected over a time period.
- 📝Note: adetection use case is made up of conditions, correlation rules and/or machine learning algorithms applied to specific indicators (e.g. transfer amount of more than $50K)
- Why: Breakdown of indicators that make up each fraud use case gives a more granular understanding of the activities and behaviors observed in your environment, and allows you to investigate and take decisions on the next course of action in response to the detections.
- How: Forward data from your product or services (e.g. transaction system, applications, APIs, security tools, contextual information such as identity / asset / consumer data) to build, configure, and monitor fraud use cases on the hm.works platform.
* * *
And that is hm.works 1.10! We will be releasing more features and updates regularly, so stay tuned.
To get the latest news from Human Managed, follow us on LinkedIn and check out our blog.
* * *
Want to discuss how we can help solve your cyber, digital, or risk operations through data?
Want a test run of the hm.works app?
Have any questions or feedback?
Please contact us at hello@humanmanaged.com.