<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[DataVisor - Medium]]></title>
        <description><![CDATA[AI-powered fraud management solutions that move faster than the speed of fraud. - Medium]]></description>
        <link>https://medium.com/datavisor?source=rss----e8d9c3aaa8d6---4</link>
        <image>
            <url>https://cdn-images-1.medium.com/proxy/1*TGH72Nnw24QL3iV9IOm4VA.png</url>
            <title>DataVisor - Medium</title>
            <link>https://medium.com/datavisor?source=rss----e8d9c3aaa8d6---4</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sat, 21 Nov 2026 03:56:59 GMT</lastBuildDate>
        <atom:link href="https://medium.com/feed/datavisor" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Feature Engineering: 8 Critical Capabilities for Fraud and Risk Management]]></title>
            <link>https://medium.com/datavisor/feature-engineering-8-critical-capabilities-for-fraud-and-risk-management-d6a3e0b6f466?source=rss----e8d9c3aaa8d6---4</link>
            <guid isPermaLink="false">https://medium.com/p/d6a3e0b6f466</guid>
            <category><![CDATA[fraud-detection]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[financial-services]]></category>
            <category><![CDATA[risk-management]]></category>
            <category><![CDATA[mlops]]></category>
            <dc:creator><![CDATA[Jeremy Chen]]></dc:creator>
            <pubDate>Fri, 27 May 2022 21:21:10 GMT</pubDate>
            <atom:updated>2022-05-27T21:21:10.412Z</atom:updated>
            <content:encoded><![CDATA[<p>This might sound like a truism for data scientists, but it can’t be stressed enough: Not all data sets are created equal and, most importantly, no two use cases are identical.</p><p>Data scientists spend a substantial amount of time transforming data and making it useful. The processes of data transformation are also referred to as feature engineering because logical operations and other functions are applied to features in order to transform the data set with the goal of making it as useful as possible for the specific project at hand.</p><p><strong>Feature engineering </strong>(a.k.a. feature building or signal creation) is truly part art and part science because it is the perfect intersection of technical expertise and domain knowledge. Without a thorough understanding of the problems that the algorithm is trying to solve and all the factors that play a part in them, it would be impossible to know what questions to ask the data.</p><p>In order to be successful within fraud teams, data scientists must be empowered with advanced tools for feature engineering. This article focuses on the eight most important capabilities that they require.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*zjXDHIduODoDonnt" /></figure><ol><li><strong>Real-time feature computation on demand</strong></li></ol><p>Modern fraud data scientists must be equipped with tools that allow them to compute features on the spot to avoid an issue referred to as staleness. Staleness occurs when data takes time to refresh, and features are calculated in old sets that no longer reflect reality. Staleness causes poor performance of the ultimate fraud detection actions and poses a serious concern for organizations.</p><p>In cases such as where bot attacks are present, systems must be able to capture and compute real signals within milliseconds and at an event level in order to stay ahead of fast-moving attackers. Vendors that offer “near real-time” capabilities fail to deliver the detection precision required by modern businesses that risk falling prey to more sophisticated fraudsters.</p><p><strong>2. Native integration between features and rules and models</strong></p><p>Feature computation is critical, but good features are of no use unless they are properly integrated with the models and business rules that ultimately deliver the detection capabilities.</p><p>Systems where rules and models are built in unison from the start outperform their peers by delivering detection capabilities without the errors and delays that may result from integration issues between data mapping and data pipelines at the future serving layer and the business rules and model training environment.</p><p><strong>3. Fraud and compliance functionalities by design</strong></p><p>Marketing, logistics, and other specialists use feature engineering too, but their use cases and goals are not the same as fraud leaders’. Fraud teams face unique challenges, and having a feature engineering platform that is purpose-built with the sole purpose of overcoming them can mean all the difference in the world.</p><p>Sure, off-the-shelf products can be adapted into fraud environments, but it generally makes more sense to allow fraud experts to focus on what really matters instead: developing and improving their fraud and risk strategies.</p><p>For example, having fraud-specific feature packages that are ready to use from day one can enable fraud teams to run their detection models and rules logics with speed and confidence from day one, instead of having to build everything from scratch.</p><p>When choosing a feature engineering platform, it is important to look for a provider that has deep domain expertise to build on top of years of experience and avoid all the missteps and course corrections that product development naturally entails.</p><p><strong>4. Multidimensional and native graph features</strong></p><p>Real life is complex and if data sets intend to reflect it, they must be too. Modern fraud teams need:</p><ul><li>Multidimensional graph features that can leverage multiple vectors including history, geolocation, relationships between users to combat sophisticated crime rings.</li><li>Graph databases that can use graph structures for semantic queries with nodes, edges, and properties to represent and store large quantities of data.</li><li>Intuitive graph structures that can portray the complex relationship between entities in innovative and actionable ways that make feature engineering more efficient.</li></ul><p><strong>5. Fast backfill and deployment without IT</strong></p><p>In most modern organizations, IT teams’ work is spread across different functional areas. Fraud data scientists must be empowered to deploy the features they have prepared and warm them up through backfills without having to depend on IT support. The result: Agile fraud teams.</p><p><strong>6. Business-user friendly UI with governance</strong></p><p>No matter how much modern feature engineering solution developers strive to create simple products, the fact of the matter is that their product is a technical one that is built for a technical audience: fraud data scientists. These specialists often have many years of experience and are comfortable with concepts and terminology that is not necessarily shared by other members of their teams.</p><p>In order to fight fraud more effectively, modern enterprises need feature engineering solutions that are delivered in tandem with business-user friendly interfaces, especially in connection with governance and performance monitoring capabilities.</p><p><strong>7. Data scientist language support</strong></p><p>Trust modern solutions that data scientists can use in the programming languages they are already proficient in.</p><p>With data scientists’ salaries at an all-time high, it makes little sense to hire highly skilled workers and put them through the learning curve of new programming languages before they can start delivering value for their teams.</p><p>Furthermore, firms concerned with vendor lock-in should steer clear of feature engineering solutions that use proprietary programming languages because this characteristic acts as a clear increase in switching costs.</p><p>Prefer solutions that support Python, Java and SQL to define features and save yourself and your data scientists a lot of effort.</p><p><strong>8. Consistency in computation results across development stages and between batch and real time</strong></p><p>Modern data science teams need reliable systems that deliver results their entire teams can trust, and nothing kills trust more than lack of consistency. It is critical that feature computation be supported with the same technology and quality in a development environment or in production. Offline or in real time too.</p><p><strong>Conclusion:</strong></p><p>All in all, feature engineering plays such a relevant role in modern fraud prevention because the data it transforms must lay the foundation of the detection efforts and the ultimate decisions taken to alleviate fraud. Investing in the right solution for fraud-specific purposes can really pay off, especially when thinking in the long term and at scale.</p><p>My team at DataVisor develops cutting-edge technology to deliver on these capabilities and bring customers’ fraud and risk management strategies to the next level with a focus on addressing real business challenges.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*sfuKLv1mU-ZjwUJQ" /></figure><p>Many thanks to <a href="https://medium.com/u/b3178f138469">Eduardo Guraieb</a> for your original ideas for this article.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=d6a3e0b6f466" width="1" height="1" alt=""><hr><p><a href="https://medium.com/datavisor/feature-engineering-8-critical-capabilities-for-fraud-and-risk-management-d6a3e0b6f466">Feature Engineering: 8 Critical Capabilities for Fraud and Risk Management</a> was originally published in <a href="https://medium.com/datavisor">DataVisor</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[DataVisor Global Fraud Watch June 2021]]></title>
            <link>https://medium.com/datavisor/datavisor-global-fraud-watch-june-2021-c7ff94fae57c?source=rss----e8d9c3aaa8d6---4</link>
            <guid isPermaLink="false">https://medium.com/p/c7ff94fae57c</guid>
            <dc:creator><![CDATA[Parinitha Marnekar]]></dc:creator>
            <pubDate>Fri, 25 Jun 2021 13:01:20 GMT</pubDate>
            <atom:updated>2021-06-25T13:01:16.475Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*JfjLfT8zVHeerOWW" /></figure><p>Organizations of all sizes and across all industries can benefit from knowing the potential types of fraud they face. DataVisor creates this monthly Global Fraud Trends report because getting better at identifying fraud begins with achieving greater fraud awareness.</p><p>This month’s global fraud and risk report demonstrates the need for advanced fraud solutions to reduce vulnerability and improve your overall fraud detection and prevention efforts.</p><h3>Children Can Be Targets of Identity Theft, Too</h3><p>Detecting stolen identities is a goal for any fraud prevention solutions, but what about when those identities belong to children? This was the case for one Tacoma woman who stole and used the identities of 13 American Samoa children, along with the identity of her deceased ex-husband, to claim benefits to which she wasn’t entitled. The amount totaled $276,000 over the course of seven years. The women used the identities to open bank accounts and credit cards as a form of “free money.”</p><p><strong>The Takeaway: </strong>Knowing more about a customer’s profile, such as age and birth date, can help to detect fraud involving children’s identities.</p><h3>Elderly Citizens are Targets of Fraud</h3><p>The elderly are among the most vulnerable population, which is why fraudsters conduct scams to target them directly. In one recent case, more than 10 people were caught, tried, and sentenced in a large-scale scheme to exploit elderly citizens.</p><p>The group conducted robocalls using a call center in India, claiming the elderly victims had a legal matter that required their immediate attention. What’s more, the calls claimed that the victims faced severe consequences if they failed to act.</p><p>Once the victims accepted the call, they were transferred to another individual impersonating the FBI, DEA, SSA, or other official group. The goal was to have the victim wire or transfer money to the fraudsters. The estimated sum of the damage was roughly $152.9 million, but may be larger since not all elderly victims report all of their losses.</p><p><strong>The Takeaway: </strong>Suspicious spending or money transfer patterns from elderly citizens (or any customer, for that matter) may indicate potential fraudulent activity.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/600/0*xD4BycWEQWELfB6K" /></figure><h3>Coronavirus Fears Open the Door to Fraud</h3><p>Any time of uncertainty will lead to fear of that uncertainty. Fraudsters are quick to take advantage of this fear, which was the case with one phishing scam when many were working remotely.</p><p>Fraudsters circulated an email that looked as though it came from the CDC, claiming to show the viewer a list of updated COVID cases in their city. The link, however, opened an Email Reply box with the sender’s email domain as “@cdc-gov.org,” with the goal of collecting personal information about the email recipients. A similar email scam was sent requesting money to fight the coronavirus.</p><p><strong>The Takeaway: </strong>Consumers should be their own advocates against fraud by looking for inconsistencies (e.g., misspellings, etc.) that indicate fraud.</p><p>Fight fraud proactively. <a href="https://www.datavisor.com/trial/?utm_source=medium&amp;utm_medium=blog&amp;utm_campaign=mediashower"><strong>Get a demo</strong></a> to watch DataVisor’s AI-powered fraud prevention platform in action today.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/680/0*KXItuE7bxye5ftvo" /></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=c7ff94fae57c" width="1" height="1" alt=""><hr><p><a href="https://medium.com/datavisor/datavisor-global-fraud-watch-june-2021-c7ff94fae57c">DataVisor Global Fraud Watch June 2021</a> was originally published in <a href="https://medium.com/datavisor">DataVisor</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[DataVisor Global Fraud Watch May 2021]]></title>
            <link>https://medium.com/datavisor/datavisor-global-fraud-watch-may-2021-c26a321a43fc?source=rss----e8d9c3aaa8d6---4</link>
            <guid isPermaLink="false">https://medium.com/p/c26a321a43fc</guid>
            <dc:creator><![CDATA[Parinitha Marnekar]]></dc:creator>
            <pubDate>Fri, 28 May 2021 13:02:41 GMT</pubDate>
            <atom:updated>2021-05-28T13:02:41.001Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*ZWuo5fA3VnQHs_tA" /></figure><p>Global fraud trends can give organizations an inside look at threats that might affect their business. They create fraud awareness and highlight the ongoing need for advanced fraud solutions to protect your company, employees, and customers. Here’s our May Global Fraud and Risk Report with some of the key takeaways from the past month.</p><h3>Identifying Fraud in PPP Continues</h3><p>A recent fraud case involving the Paycheck Protection Program shows the value in finding discrepancies in data. One Oklahoma businessman applied for a PPP loan, stating he had $40K in monthly payroll costs between five employees. However, the gap between what he claimed on his loan application vs. what he reported in paycheck withholdings was a dead giveaway that the loan was fraudulent.</p><p>Fraud solutions like DataVisor leave no stone unturned when it comes to identifying fraud. Even transactions that seem legitimate on the surface may have underlying details that don’t add up.</p><h3>Fraud Can Take Years to Uncover</h3><p>One recent fraud case spans 17 years, indicating that the longer someone can get away with their activities, the longer they engage in them. One woman in Montana received $325,000 in government benefits over the course of 17 years by lying to the Social Security Administration about her marital status, income, and living arrangements. Verifying all of the above can require multiple layers of investigation, which is why a multi-layered approach to fraud detection is such an important asset in identifying fraud.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/600/0*dseMVmr3OQWmOrgv" /></figure><h3>Large-Scale Crime Rings Can Happen in Plain Sight</h3><p>Medical insurance scams involving multiple providers and patients can be difficult to uncover because their span is so wide. And in many cases, some of the players may not even realize they are committing fraud in the first place.</p><p>This was the case with a natural wellness clinic in California. The owner, a chiropractor, targeted Medicare and TRICARE patients and instructed his staff to offer treatments, tests, and durable medical equipment to every patient, even if it wasn’t needed. When services didn’t qualify for insurance payment (which happened to be the majority of services provided by the clinic), the facility incorrectly billed the insurance companies using physical therapy codes, even though the providers performing the treatments weren’t licensed to perform physical therapy procedures.</p><p>The scheme extended into worker’s compensation, offering to provide a certain amount of durable medical equipment for every worker’s comp patient referred to his clinic. In total, the worker’s comp scheme collected more than $6.6 million in bills and affected 529 patients.</p><h3>Advanced Fraud Solutions to Combat Global Fraud Trends</h3><p>The above examples of fraud are multi-layered and require deep, time-consuming investigation to unravel. Advanced fraud solutions like DataVisor support fraud prevention and detection efforts to identify hidden connections between bad actors and activities.</p><p><a href="https://www.datavisor.com/trial/?utm_source=medium&amp;utm_medium=blog&amp;utm_campaign=mediashower"><strong>Learn more about DataVisor fraud prevention solutions</strong></a> to stay ahead of global fraud trends as they evolve.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/680/0*PY_gKq0ojpZQ7PpC" /></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=c26a321a43fc" width="1" height="1" alt=""><hr><p><a href="https://medium.com/datavisor/datavisor-global-fraud-watch-may-2021-c26a321a43fc">DataVisor Global Fraud Watch May 2021</a> was originally published in <a href="https://medium.com/datavisor">DataVisor</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[DataVisor Global Fraud Watch April 2021]]></title>
            <link>https://medium.com/datavisor/datavisor-global-fraud-watch-april-2021-a77c51b329ca?source=rss----e8d9c3aaa8d6---4</link>
            <guid isPermaLink="false">https://medium.com/p/a77c51b329ca</guid>
            <category><![CDATA[fraud-and-risk]]></category>
            <category><![CDATA[global-fraud]]></category>
            <dc:creator><![CDATA[Parinitha Marnekar]]></dc:creator>
            <pubDate>Fri, 30 Apr 2021 13:03:54 GMT</pubDate>
            <atom:updated>2021-04-30T13:03:52.178Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*crez9_723DesC16O" /></figure><p>No business or organization wants to be on the receiving end of fraud. However, no one is ever completely immune from fraudsters, either. One strategy in identifying fraud and helping you mitigate this possibility is to learn from others’ misfortune. Fraud awareness is an essential piece of the fraud prevention puzzle. These recent cases of fraud illustrate global fraud trends that could make their way into your business.</p><h3>Medicare Scam Unveiled Due to Bad Math</h3><p>Internal fraud is hard enough to detect when it’s your employees committing the crime. But what happens when it’s the owner of the business?</p><p>The owner of a rehabilitative mental health clinic tried to siphon nearly $500,000 from Medicare, stating she provided more than 24 hours of service to Medicare beneficiaries every day over the course of several months. Medicare auditors noticed her claims didn’t quite add up and were able to uncover the scam.</p><h3>PPP Fraud Continues to Unveil Itself</h3><p>When the Paycheck Protection Program was first unveiled, it caught the eyes of legitimate business owners and fraudsters alike because the bar to entry was relatively low. Very little documentation had to be provided to acquire the funds, plus the loans would be eligible for forgiveness later.</p><p>Nearly a year later, we are seeing the effects of scammers trying to beat the system.</p><p>One man in Florida has been caught trying to obtain more than $1.5 million in PPP loan money over the course of nine loan applications. Alongside his own name, he stole the identities of eight elderly individuals (one was a family member and the other seven lived in assisted living facilities). Applications were submitted to nine different credit unions and banks to avoid detection. What’s more, the businesses the loan money was intended for didn’t exist.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/600/0*5wd30m5KQ3vLeXLJ" /></figure><h3>The Man with 35 Faces</h3><p>In many cases, fraud is conducted on a large scale among multiple entities. This was partly the case with a Georgia man who stole 35 identities to carry out his fraud attempts. He exploited the ease and visual concealment that comes with online banking to open unfunded accounts across multiple banks.</p><p>He used the accounts to transfer fraudulent funds from one account to the next, even though there were no funds to support the transfers. The accounts would show an anticipated balance, which the man used to pay off student loans and credit card debt and would do so before the banks realized no funds were actually coming through. The total cost of his misdeeds: $185,000+.</p><p>It’s noted that this type of banking fraud is very difficult to identify and even harder to trace. This underscores the growing need for advanced fraud solutions that can cover all types of threats in real time.</p><p>Want to learn more about how Datavisor can help you improve fraud detection? We can help with that. <strong>R</strong><a href="https://www.datavisor.com/trial/?utm_source=medium&amp;utm_medium=blog&amp;utm_campaign=mediashower"><strong>equest a demo</strong></a> and experience the power of proactive AI-powered fraud prevention today.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/680/0*F2J-6PjpWHbZUuCG" /></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=a77c51b329ca" width="1" height="1" alt=""><hr><p><a href="https://medium.com/datavisor/datavisor-global-fraud-watch-april-2021-a77c51b329ca">DataVisor Global Fraud Watch April 2021</a> was originally published in <a href="https://medium.com/datavisor">DataVisor</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[DataVisor Global Fraud Watch March 2021]]></title>
            <link>https://medium.com/datavisor/datavisor-global-fraud-watch-march-2021-80e5655c8ff6?source=rss----e8d9c3aaa8d6---4</link>
            <guid isPermaLink="false">https://medium.com/p/80e5655c8ff6</guid>
            <dc:creator><![CDATA[Parinitha Marnekar]]></dc:creator>
            <pubDate>Tue, 30 Mar 2021 17:03:25 GMT</pubDate>
            <atom:updated>2021-03-30T17:03:24.787Z</atom:updated>
            <content:encoded><![CDATA[<p>Identifying fraud in today’s multi-layered landscape is complex, but not impossible. Our global fraud watch follows three fraudsters who got caught.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*j-_fyuMHlIK4Up_7" /></figure><p>One of the top global fraud trends of late is that fraudsters continue to push the boundaries of creativity to commit crimes. Stealing more than paltry sums, cybercriminals operate under the belief that big risks are worth the potentially huge sums that come with a successful heist. However, an increase in fraud awareness and improved fraud detection and prevention efforts are narrowing their windows of opportunity. Here’s a closer look at our latest global fraud and risk watch.</p><h3>Turning Identity Theft into a Vacation</h3><p>Traveling 1,000 miles to commit identity fraud can be an expensive endeavor, especially when you get caught. But the risks didn’t stop two men from booking a flight from New York to New Orleans, where they tried to open a $4,000 credit line using a stolen identity at a Best Buy in Baton Rouge. What’s interesting is that the Louisiana Financial Crimes Task Force was hot on their heels before their plane even landed.</p><p>Advanced fraud solutions that include real-time functionality can enable quick action like this.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*e6kNsrUEYnncImrs" /></figure><h3>Jailbirds Don’t Qualify for CARES Act Funds</h3><p>CARES Act unemployment benefits only apply to those who were put out of work due to the pandemic. However, some citizens in Pennsylvania didn’t get the memo.</p><p>Inmates were found to be using cell phones in jail to contact people outside the prison to file for benefits under the Pandemic Unemployment Assistance Program. Anyone assisting prisoners with filing for benefits is considered to be acting on their behalf. In one case, a man’s girlfriend used her own address to file for his benefits, making her culpable in the case.</p><p>In total, she received about $11,000 due to her illegal actions, which she agreed to return. However, this doesn’t excuse her from potentially facing up to 30 years in prison, a fine of up to $250,000, or both.</p><h3>CARES Act Fraud is Actually an Uncaring Act</h3><p>Paycheck Protection Program fraud has run rampant since the Act’s introduction early in the pandemic.<a href="https://www.nytimes.com/2020/09/10/us/politics/ppp-fraud-coronavirus.html#"> Billions of dollars</a> have been estimated to have been lost to fraud, and so far,<a href="https://www.washingtonpost.com/business/2020/09/10/ppp-fraud-charges/"> 57 people have been officially charged</a>, with many more likely on the way.</p><p>One recent case is a 52-year old man’s attempt to steal and launder $1.2 million in PPP funds. In total, he submitted more than 20 loan applications for various businesses he claimed to own, citing 120+ employees with more than $5 million in payroll expenses.</p><p>His claims couldn’t pass fraud detection, though. He was found to own and operate zero businesses and was therefore ineligible for loan money. Authorities are now working to find his accomplices in the large-scale scheme.</p><p>Identifying fraud is becoming increasingly complex as fraudsters commit their crimes across myriad channels. Investing in top fraud prevention solutions can help companies to mitigate their risk and proceed with business as usual.</p><p><a href="https://www.datavisor.com/intelligence-center/e-book/ppp-loan-risk/?__mscta=2698_86751_11343">Say ahead of PPP loan fraud</a> .</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/680/0*vCJMXhmaJ0vRRAY2" /></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=80e5655c8ff6" width="1" height="1" alt=""><hr><p><a href="https://medium.com/datavisor/datavisor-global-fraud-watch-march-2021-80e5655c8ff6">DataVisor Global Fraud Watch March 2021</a> was originally published in <a href="https://medium.com/datavisor">DataVisor</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[The New MacBook Could Be A Secret Weapon for Fraudsters]]></title>
            <link>https://medium.com/datavisor/the-new-macbook-could-be-a-secret-weapon-for-fraudsters-6dcf0927c321?source=rss----e8d9c3aaa8d6---4</link>
            <guid isPermaLink="false">https://medium.com/p/6dcf0927c321</guid>
            <category><![CDATA[macbook]]></category>
            <category><![CDATA[d-edge]]></category>
            <category><![CDATA[fraud]]></category>
            <dc:creator><![CDATA[Parinitha Marnekar]]></dc:creator>
            <pubDate>Fri, 26 Mar 2021 13:03:29 GMT</pubDate>
            <atom:updated>2021-03-26T13:03:25.697Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*5q4JI6d2m2QGFQW3" /></figure><p>Last November, Apple unveiled the M1 chip, abandoning the Intel x86 architecture CPU processor that had been used in its MacBook line since 2005. Loyal Apple fans marvel at the new MacBook’s tripled speed, longer battery life, and advantageous price.</p><p>This is likely why no one is talking enough about its serious security flaw.</p><h3>MacOS Could Leave Users Vulnerable</h3><p>The new Mac iOS causes permission invalidation data streaking. Because macOS is open, users and programs on the Mac are allowed to obtain system root permissions. This isn’t the case with closed-system iOS, which limits the permissions of users and programs on the iPhone. This causes the macOS program to perform arbitrary operations on the iOS program when mobile phone apps run on macOS. This means that the existing mobile application risk control mechanism may be severely impacted.</p><h3>App Sandbox to Become a Transparent Box?</h3><p>The permissions of iOS cannot know the changes of the macOS layer. If the mobile app runs on macOS, the user’s privacy data of the mobile app can be read and modified casually by macOS with higher authority.</p><p>Originally, the closed system of the iPhone was not easy to read unless the device was jailbroken. Files in the App sandbox were safe and confidential. Now, all iOS app data running on the Mac is placed in the user directory. The app sandbox has now become a transparent box.</p><p>iOS app data is not protected at the macOS layer. This means that every Apple computer becomes a potential hotbed of black production. It will be easy to perform batch multi-opening, proxy, and code on Apple computers. What’s more, the mobile terminal risk control system will be invalidated.</p><h3>A Risk Bomb without Barriers</h3><p>The installation of mobile apps on Mac M1 is without barriers. The unpacked IPA (Apple program application file) can be installed and run directly on MacBooks with M1 chips. For attackers, the operation is simple: Write a macOS program with root privileges and inject it into the iOS runtime. Attackers can debug and attack the iOS application through the Mac, readout, and tamper with the iOS program data.</p><h3>Security Solutions for M1 Defense</h3><p>The new MacBook with the M1 chip is likely to quickly become a treasure of fraud attackers. An M1 MacBook can run hundreds of apps, including iOS apps. It may become a Black Market “tool warehouse” and the cost of conducting mobile fraud will be greatly reduced.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*nM7vErbgP8pnMOLG" /></figure><p>In response, DataVisor’s dEdge, a cutting-edge device intelligence solution, launched new fraud detection functions adapted to the M1 chip:</p><h3>Reliable Device ID (DVID) on Mac</h3><p>DataVisor provides the only true and stable DVID for the device, which means that when one application or hundreds applications are running on the same MacBook device, DVID is reliable evidence to identify the operating environment.</p><h3>Local data encryption to prevent random modification of the sandbox</h3><p>dEdge fraud prevention provides strong security encryption for the App sandbox. Based on the data signature developed by DataVisor, a more difficult algorithm protection barrier is added to the unique characteristics of traditional digital signatures. Data can be encrypted locally and each machine owns their encrypted keys. To protect the key security, the encryption strength is extremely high, and there is no effective cracking scheme so far. This ensures the safety and reliability of the data while preventing cracking and random modification.</p><h3>Effective identification of iOS apps on Mac M1</h3><p>DataVisor’s dEdge can identify the operating environment of iOS apps and give a scientific operating environment risk score. When it is discovered that iOS apps are running on the Mac, dEdge can promptly alert and set protection strategies in real time.</p><h3>Interception of fraud attacks of simulators on the M1 chip</h3><p>dEdge fraud detection software has powerful attacker detection capabilities, which can identify abnormal behaviors of iOS applications during runtime, such as: jailbreak, hook, multi-open, modify code, black box calls, and more. dEdge, combined with DataVisor’s patented unsupervised machine learning algorithm, can also effectively identify the entire attack group and even issue risk warnings during the early registration stage or app download stage before the attack occurs.</p><p>Under the protective wings of dEdge, attacks from black market based on the M1 chip will have nowhere to hide. Want to discover more about our fraud detection software solutions? <a href="https://www.datavisor.com/intelligence-center/ebooks/fight-synthetic-fraud-with-a-multi-layered-detection-platform/?utm_source=website&amp;utm_medium=medium&amp;utm_campaign=mediashower">Request a demo today!</a></p><figure><img alt="Request Demo" src="https://cdn-images-1.medium.com/max/611/1*MkwUoMjw0APyTC2eKUS0fg.png" /></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=6dcf0927c321" width="1" height="1" alt=""><hr><p><a href="https://medium.com/datavisor/the-new-macbook-could-be-a-secret-weapon-for-fraudsters-6dcf0927c321">The New MacBook Could Be A Secret Weapon for Fraudsters</a> was originally published in <a href="https://medium.com/datavisor">DataVisor</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[DataVisor Global Fraud Watch Feb 2021]]></title>
            <link>https://medium.com/datavisor/datavisor-global-fraud-watch-feb-2021-8731b492a798?source=rss----e8d9c3aaa8d6---4</link>
            <guid isPermaLink="false">https://medium.com/p/8731b492a798</guid>
            <dc:creator><![CDATA[Parinitha Marnekar]]></dc:creator>
            <pubDate>Fri, 26 Feb 2021 14:04:15 GMT</pubDate>
            <atom:updated>2021-02-26T14:04:12.201Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*qMmqef7hVHB5UUeg" /></figure><p>Public assistance fraud and identity theft are not unique to the current landscape, but the global pandemic could be to blame for an increase in fraud. Many states have been hard hit by fraudsters filing false unemployment claims or other assistance benefits. And even though there is now a vaccine, it’s still anyone’s guess as to when “normal” life might resume. This means that keeping your finger on the pulse of fraud continues to be a top priority.</p><p>Awareness plays a big role in fraud prevention. Here’s a closer look at the face of fraud in February 2021 to help you stay vigilant:</p><h3>$1.2 Million in PPP Loan Fraud</h3><p>The Paycheck Protection Program (PPP) was originally designed to help small business owners continue paying their employees and take care of ongoing expenses during the early days of the pandemic. Businesses could borrow up to 2.5 times their salary expenses over the course of two months, and loans were eligible for forgiveness.</p><p>However, the program was hastily assembled, and very little to no vetting processes were established. This led to many lenders giving money to businesses that did not qualify, including businesses that weren’t “businesses” at all.</p><p>One major example of this is a recent case in California, in which 40-year old Santa Clarita resident Raymond Magana pleaded guilty to fraudulently obtaining $940,416 in PPP funding. On his application, Magana’s business, The Building Circle LLC, claimed he had 40 workers and $376,167 in monthly payroll. To support his claim, Magana provided false tax documents that highlighted $4,402,000 in annual wages for 2019. Magana transferred the loan money to his shell company, then applied for another $360,415 in PPP funding for another company.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*_L9nUem1cxys192Z" /></figure><h3>Trading SNAP Benefits for Cash</h3><p>SNAP benefits can be used to purchase a variety of non-prepared foods. Benefits are added to a card and spent on qualifying items just like cash. But one rule that’s clear is that the money isn’t intended to be turned into cash.</p><p>The owner of a seafood market and restaurant recently admitted to his role in an 8-year scheme that traded SNAP benefits for cash.</p><p>A court document stated that the SNAP redemptions at his store exceeded the state of Virginia’s average for all other seafood specialty stores by more than $2.4 million. This difference captured the attention of officials, which spurred an investigation.</p><h3>Social Security Fraud Can Be an Inside Job</h3><p>Social security fraud doesn’t always come from false claims and beneficiaries. One recent inside job directed more than $236,000 in benefits to an employee’s own bank account. The employee used multiple fictitious identities mixed with identities of real people.</p><p>He had access to documents (e.g., passports, ID cards, marriage licenses) for claimants who lived abroad and used bits and pieces of their data to formulate his own identities. Claims for survivor’s benefits against deceased individuals were his specialty, using his home address and an address in Canada before being discovered.</p><p><a href="https://www.datavisor.com/group-demo/?utm_source=homepage_slider&amp;utm_medium=website&amp;utm_campaign=GroupDemo_1015&amp;__mscta=2862_86324_11343"><strong>Watch DataVisor fight fraud. Join our bi-weekly demo.</strong></a></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/680/0*olaJEf-PD2LBzgAs" /></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=8731b492a798" width="1" height="1" alt=""><hr><p><a href="https://medium.com/datavisor/datavisor-global-fraud-watch-feb-2021-8731b492a798">DataVisor Global Fraud Watch Feb 2021</a> was originally published in <a href="https://medium.com/datavisor">DataVisor</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[DataVisor Global Fraud Watch January 2021 Edition]]></title>
            <link>https://medium.com/datavisor/datavisor-global-fraud-watch-january-2021-edition-bc5c9a9d1249?source=rss----e8d9c3aaa8d6---4</link>
            <guid isPermaLink="false">https://medium.com/p/bc5c9a9d1249</guid>
            <category><![CDATA[covid19]]></category>
            <category><![CDATA[fraud-detection]]></category>
            <category><![CDATA[healthcare]]></category>
            <dc:creator><![CDATA[Parinitha Marnekar]]></dc:creator>
            <pubDate>Fri, 29 Jan 2021 14:03:28 GMT</pubDate>
            <atom:updated>2021-01-29T14:03:24.488Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*Q4_py3KRLm-S8yqb" /></figure><p>The effects of the 2020 global pandemic coupled with uncertainty have spilled over into the new year. A flip of the calendar hasn’t exempted companies from maintaining a watchful eye over fraud trends. Learning how fraud occurs and the lengths people will go to are impactful first steps in reviewing your own fraud detection and prevention strategies. Here’s a closer look at recent fraud cases that prove you can never be too careful:</p><h3>Fraud Detection Challenges of Skimming</h3><p><a href="https://www.fraudoftheday.com/uncategorized/skimming/"><strong>Skimming</strong></a> is a common method of fraud in which the thief takes “a little off the top” with the hope that no one will notice. Over time, bits of stolen funds can add up to serious cash and hefty losses to the business.</p><p>That’s when a person’s skimming activities can suddenly catch up to them. Giovanne Gomez, a manager at a nursing care service in Rhode Island, was recently accused of and tried for a skimming scheme involving the Medicaid program. Gomez allegedly created 30 fake timesheets for CNAs whom she said provided care services for 100 beneficiaries, resulting in a $120,000+ payout from Medicaid. She then diverted the funds into two bank accounts owned by her husband’s business.</p><p>Both Gomez and her husband were convicted after the couple used the account to make cash withdrawals, wire transfers, and tendered checks.</p><h3>COVID Crime Adds to Fear, Uncertainty, and Hardships</h3><p>For millions of citizens and business owners, the COVID-19 pandemic wasn’t just a public health crisis. It was also a year filled with financial hardships, fear, and anxiety. For someone to exploit others for their own financial gain during this time is underhanded and appalling — and yet it’s all too common.</p><p>Baltimore resident Nicholas White was convicted of<a href="https://www.fraudoftheday.com/covid-19-fraud/covid-feature-unprecedented-fraud/"> <strong>collecting CARES Act benefits</strong></a> intended to provide aid to struggling workers. To access these benefits, he stole personal identifying information from his victims. He also intercepted an economic relief payment intended for a couple living in Maryland, and deposited it into an account he opened using a victim’s name, birth date, and social security number.</p><p>This act was only the latest in a series of fraud-related crimes spanning multiple months. White was also found to be involved in a massive mail theft scheme, used counterfeit money to purchase firearms, and used fake PII to qualify for a loan to purchase a Maserati.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*kY2hqXAqyb9esU3I" /></figure><h3>COVID Fraud Increases Health Risks</h3><p>Two Texas men were recently charged in a<a href="https://www.fraudoftheday.com/covid-19-fraud/covid-feature-the-wizards-of-fraud/"><strong> $317 million fraud scheme</strong></a> wherein they attempted to sell highly-coveted N95 masks to a foreign government. Toward the beginning of the pandemic in the United States, N95 masks were in short supply and high demand, opening the door to a bevy of fraud. In this case, the two fraudsters tried to sell 50 million masks at a 500% markup compared to the normal selling price — despite the fact that their stock of masks didn’t exist.</p><p>The government wired the money to the two criminals, but the transaction was thwarted by the Feds and the two men were captured.</p><p>We are still living in desperate times, and the need for proactive fraud detection and prevention has never been greater. <a href="https://www.datavisor.com/group-demo/?utm_source=homepage_slider&amp;utm_medium=website&amp;utm_campaign=GroupDemo_1015&amp;__mscta=2860_85812_11343"><strong>Watch DataVisor fight fraud. Join our bi-weekly demo</strong></a><strong>.</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/680/0*pkpMcEe_gBTky1SH" /></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=bc5c9a9d1249" width="1" height="1" alt=""><hr><p><a href="https://medium.com/datavisor/datavisor-global-fraud-watch-january-2021-edition-bc5c9a9d1249">DataVisor Global Fraud Watch January 2021 Edition</a> was originally published in <a href="https://medium.com/datavisor">DataVisor</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[DataVisor Global Fraud Watch: November 2020 Edition]]></title>
            <link>https://medium.com/datavisor/datavisor-global-fraud-watch-november-2020-edition-45299838acc1?source=rss----e8d9c3aaa8d6---4</link>
            <guid isPermaLink="false">https://medium.com/p/45299838acc1</guid>
            <dc:creator><![CDATA[Priya Rajan]]></dc:creator>
            <pubDate>Tue, 01 Dec 2020 17:27:43 GMT</pubDate>
            <atom:updated>2020-12-01T17:27:43.191Z</atom:updated>
            <content:encoded><![CDATA[<p><strong>DataVisor Global Fraud Watch: November 2020 Edition</strong></p><p>Meta: As the end of the year draws closer, it’s important to remember that fraud never takes a holiday. Here are some recent examples of fraud cases.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*P5sthWdRR1Sqfnl-" /></figure><p>As the holiday shopping season begins, retailers know that consumers aren’t the only ones looking to cash in on good opportunities. Fraudsters are doing their part to keep companies on their toes by exploiting loyalty programs and offers, rerouting packages, taking over accounts, and stealing credit card information, among other fraudulent activities.</p><p>While shopping scams tend to take center stage during the holidays, it’s important to remember that other types of fraud still pose risks, too.</p><p>’Tis the season to remain ever vigilant about the current state of fraud and understand how to protect your company from fraud risks. Here are a few of the most recent fraud stories from around the world:</p><h3>Employment Fraud: Be Careful Who You Hire</h3><p>Employers usually have strong vetting processes for choosing qualified candidates. Names and certifications might match up on paper, and their references may check out. But when those candidates aren’t actually who they say they are, it can pose a significant risk to the business and the customers it serves.</p><p>This is what happened in a years-long fraud case where one Michigan woman posed as a medical professional and scammed multiple employers out of more than $2.2 million. Posing as a registered nurse, she used the license numbers of real nurses to earn prestigious positions in various healthcare firms. Her most recent job was for a medical consulting firm, which offered her a salary of $285,000 per year.</p><p>The woman had no medical training or experience, which not only put the people she consulted with at risk, but also jeopardized the reputation of the companies for which she worked.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*SKeQ90IIwOoofzW4" /></figure><h3>Check Cashing Scheme Spans 12 States and Over 5,000 Checks</h3><p>Even in a world driven by credit cards and contactless payments, checks are still widely used by many. One of the biggest problems is that many retailers don’t have a way to verify a check’s validity on the spot, which makes it easy for check fraud to run rampant.</p><p>One man recruited a few helpers to run a check-cashing scheme in multiple Kroger grocery stores. The team purchased merchandise and gift cards in Krogers across 12 states using more than 30 made-up names and companies. He was finally caught when using a fake license to purchase a car at an Illinois dealership. By this point, though, the team had racked up about $300,000 in personal gains.</p><h3>Employees Aren’t the Only Ones Who Commit Fraud in the Workplace</h3><p>It’s not uncommon to hear of employees embezzling from their employers, but this process also works in reverse. A hotel owner used an employee’s identity to finance upgrades to his hotel, including 110 flatscreen TVs and other merchandise to improve the guest experience. In total, the hotelier racked up more than $500,000 in debt in the name of his employee.</p><p>Fraud happens everywhere, and detecting fraud is everyone’s responsibility. Strong fraud detection and prevention requires a proactive approach like the one that DataVisor offers.<a href="https://www.datavisor.com/group-demo/?utm_source=homepage_slider&amp;utm_medium=website&amp;utm_campaign=GroupDemo_1015&amp;__mscta=2859_84898_11343"> Watch how DataVisor fights fraud live. Join our bi-weekly demo.</a></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/680/0*6e096qBLfo7GRU8q" /></figure><p><a href="https://www.mediashower.com/img/1FE888F0-1356-11EB-A279-D5538BA8618F/DataVisor%20Global%20Fraud%20Watch-%20November%202020%20Edition_1.svg">DataVisor Global Fraud Watch- November 2020 Edition_1.svg</a></p><p><a href="https://www.mediashower.com/img/1FE888F0-1356-11EB-A279-D5538BA8618F/DataVisor%20Global%20Fraud%20Watch-%20November%202020%20Edition_2.svg">DataVisor Global Fraud Watch- November 2020 Edition_2.svg</a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=45299838acc1" width="1" height="1" alt=""><hr><p><a href="https://medium.com/datavisor/datavisor-global-fraud-watch-november-2020-edition-45299838acc1">DataVisor Global Fraud Watch: November 2020 Edition</a> was originally published in <a href="https://medium.com/datavisor">DataVisor</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Beyond KYC: How AI Risk Detection Software Helps Banks Combat Modern Fraud]]></title>
            <link>https://medium.com/datavisor/beyond-kyc-how-ai-risk-detection-software-helps-banks-combat-modern-fraud-84ed444f3c4b?source=rss----e8d9c3aaa8d6---4</link>
            <guid isPermaLink="false">https://medium.com/p/84ed444f3c4b</guid>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[identity-theft]]></category>
            <category><![CDATA[kyc]]></category>
            <category><![CDATA[fraud]]></category>
            <category><![CDATA[ai]]></category>
            <dc:creator><![CDATA[DataVisor]]></dc:creator>
            <pubDate>Mon, 09 Nov 2020 01:31:52 GMT</pubDate>
            <atom:updated>2020-11-09T01:31:51.954Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*krKcTD2ETw2C_Wbs0yD_Uw.png" /></figure><p><em>As fraud activities grow in sophistication, so should the technologies used to combat them. Here’s how AI risk detection software can provide further protection in addition to the traditional KYC process.</em></p><p>Despite the ongoing development of sophisticated tools and technologies to detect and combat fraud, <a href="https://www.datavisor.com/wiki/synthetic-identity-theft/?utm_source=Blog&amp;utm_medium=blog&amp;utm_campaign=Mediashower">synthetic identity theft</a> and money laundering continue to plague organizations in a myriad of industries. It’s a seemingly endless game of tug-of-war, where technology companies must continually up the ante to fight back against fraud as criminals continue to find ways over, under, or around newly developed fraud detection methods.</p><p>Vice versa, as fraudsters become more skilled in committing illicit acts, so too must technology and software companies in detecting fraud and stopping criminals in their tracks.</p><p>One way that organizations tackle fraud issues is with the use of KYC (Know Your Customer) processes that attempt to verify the identities of their customers so they can recognize patterns in behaviors. So far, AI risk detection software is poised to play an important role in allowing KYC methods to thrive.</p><h3>What does KYC mean?</h3><p>KYC refers to the process of verifying the identities of their customers to determine the potential risk of fraud. The idea is that knowing your customers ― including personal details, spending habits, financial histories, and unique risk factors ― can reduce the chance of money laundering, terrorism financing, and other types of illicit financial activities from occurring.</p><p>KYC fraud detection consists of three core steps:</p><ol><li>Customer identification procedures</li><li>Transaction monitoring</li><li>Risk management</li></ol><p>When all three parts are addressed, financial institutions should be better positioned to differentiate between authorized and unauthorized or illegal activity.</p><h3>The Challenges of KYC in Digital Channels</h3><p>KYC isn’t just good business sense: it’s also part of maintaining compliance. Still, many organizations have unsuccessfully implemented adequate KYC detection methods in their organizations. They’ve racked up an <a href="https://www.complianceweek.com/report-financial-firms-fined-26b-for-aml-sanctions-kyc-non-compliance-since-2008/8088.article">estimated $26 billion in fines</a> related to non-compliance with AML, KYC, and sanctions over the last 10 years, not to mention the immeasurable damage to their reputation for not being in compliance.</p><p>Several challenges impede the efforts of traditional fraud modeling, particularly as digital channels continue to blur the lines in the banking industry. To date, KYC has largely relied on document-based verification, including IDs, utility bills, pay stubs, and face verification. But now, many interactions are no longer face to face: customers can open accounts via chatbots, use mobile apps to complete transactions, and place orders using voice assistance, leading to increased usage in unstructured data.</p><blockquote><em>DataVisor VP, Priya Rajan, notes the difference between structured and unstructured data:</em></blockquote><blockquote><em>“Unstructured data isn’t in the same neat and tidy package that structured data comes in because it’s being collected from a variety of channels. The emergence of structured and unstructured data has complicated KYC processes to the extent that traditional technologies cannot keep up. Reference databases like sanctions lists, while effective during an era when data was centralized, is no longer sufficient. Companies who wish to remain competitive must be able to leverage their unstructured data with confidence.”</em></blockquote><p>With data breaches, valuable information about the customer gets exposed to fraudsters who make use of these supposedly private details to create synthetic IDs that can <a href="https://www.datavisor.com/industry-solutions/financial-services/application-fraud/?utm_source=Blog&amp;utm_medium=blog&amp;utm_campaign=Mediashower">easily pass the KYC process</a>. On the operational side, increasing the volume of online applications burdens an already costly and inefficient process.</p><p>Banks are becoming more competitive with the emergence of challenger banks and are in turn offering their own digital versions of traditional banking services. With that, the need to seamlessly validate customers without increased friction and time lag is becoming more important than ever.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*vqthAY90uJsDXjju.png" /></figure><h3>Combating Fraud with Machine How AI Risk Detection Software Can Enhance KYC</h3><p>Financial institutions are considering new technology tools to address challenges to meet the heightened regulatory scrutiny and the increasing cost pressures that are affecting their KYC processes. Ideally, these tools can help with automating many of the manual processes associated with KYC.</p><p>When implemented correctly, the results are twofold:</p><ul><li>Higher accuracy and coverage; and</li><li>Greater operational efficiency</li></ul><p>Clustering and graph algorithms look at all user behavior rather than a single user. This allows companies to deliver high detection accuracy with <a href="https://www.datavisor.com/intelligence-center/ebooks/eliminating-false-positives/?utm_source=Blog&amp;utm_medium=blog&amp;utm_campaign=Mediashower">fewer false positives</a> and provide a better customer experience.</p><p>In addition, companies need the ability to identify groups of suspicious accounts based on correlated patterns at scale, but doing so can alert teams of potential fraudulent actions. This enables them to confidently make bulk decisions, but also to work through them with efficiency.</p><p>While business process automation techniques can help alleviate operational challenges associated with this increasing workload, they cannot deliver the intelligence based on big data at the real-time scale that is needed to proactively address emerging threats from crime rings and coordinated attacks.</p><p>Many existing solutions look at events in isolation or heavily rely on historical patterns to predict future risk. Not only are these solutions reactive, but in many cases, they also miss the critical signals that indicate fraud because they don’t know what to look for. This is evident in the case of bot-initiated attacks where many events look normal in isolation, but when looked at holistically are indicative of broader, organized crime activities.</p><p>To address these previously unidentified and emerging threats and acting on them before they result in fraud requires transformational thinking. The best approach should not just look at incremental solutions, but rather at solutions that can radically redefine and reshape how fraud is discovered.</p><p>In response, AI risk detection software is helping to solve KYC challenges by leveraging big data in real-time at scale. AI’s ability to monitor larger sets of data at a time can better identify larger crime rings by reviewing data holistically.</p><p>DataVisor’s unsupervised machine learning (UML) does not require historic loss labels or intense data training to detect anomalies. This allows financial institutions to proactively address potential instances of fraud as they occur rather than reactively review transactional history over time.</p><p>See DataVisor’s UML in action by <a href="https://www.datavisor.com/trial/?utm_source=medium&amp;utm_medium=mediun&amp;utm_campaign=Mediashower">requesting a free demo</a>.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=84ed444f3c4b" width="1" height="1" alt=""><hr><p><a href="https://medium.com/datavisor/beyond-kyc-how-ai-risk-detection-software-helps-banks-combat-modern-fraud-84ed444f3c4b">Beyond KYC: How AI Risk Detection Software Helps Banks Combat Modern Fraud</a> was originally published in <a href="https://medium.com/datavisor">DataVisor</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>