Skip to content

Posts tagged ‘fraud’

How To Redefine The Future Of Fraud Prevention

How To Redefine The Future Of Fraud Prevention

Bottom Line: Redefining the future of fraud prevention starts by turning trust into an accelerator across every aspect of customer lifecycles, basing transactions on identity trust that leads to less friction and improved customer experiences.

Start By Turning Trust Into A Sales & Customer Experience Accelerator

AI and machine learning are proving to be very effective at finding anomalies in transactions and scoring, which are potentially the most fraudulent. Any suspicious transaction attempt leads to more work for buying customers to prove they are trustworthy. For banks, e-commerce sites, financial institutes, restaurants, retailers and many other online businesses, this regularly causes them to lose customers when a legitimate purchase is being made, and trusted customer is asked to verify their identity. Or worse, a false positive that turns away a good customer all together damages both that experience and brand reputation.

There’s a better way to solve the dilemma of deciding which transactions to accept or not. And it needs to start with finding a new way to establish identity trust so businesses can deliver better user experiences. Kount’s approach of using their Real-Time Identity Trust Network to calculate Identity Trust Levels in milliseconds reduces friction, blocks fraud, and delivers an improved user experience. Kount is capitalizing on their database that includes more than a decade of trust and fraud signals built across industries, geographies, and 32 billion annual interactions, combined with expertise in AI and machine learning to turn trust into a sales and customer experience multiplier.

How Real-Time AI Linking Leads To Real-Time Identity Trust Decisions

Design In Identity Trust So It’s The Foundation of Customer Experience

From an engineering and product design standpoint, the majority of fraud prevention providers are looking to make incremental gains in risk scoring to improve customer experiences. None, with the exception of Kount, are looking at the problem from a completely different perspective, which is how to quantify and scale identity trust. Kount’s engineering, product development, and product management teams are concentrating on how to use their AI and machine learning expertise to quantify real-time identity trust scores that drive better customer experiences across the spectrum of trust. The graphic below illustrates how Kount defines more personalized user experiences, which is indispensable in turning trust into an accelerator.

An Overview of Kount’s Technology Stack

How To Redefine The Future Of Fraud Prevention

Realize Trust Is the Most Powerful Revenue Multiplier There Is

Based on my conversations with several fraud prevention providers, they all agree that trust is the most powerful accelerator there is to reducing false positives, friction in transactions, and improving customer experiences. They all agree trust is the most powerful revenue multiplier they can deliver to their customers, helping them reduce fraud and increase sales. The challenge they all face is quantifying identity trust across the wide spectrum of transactions their customers need to fulfill every day.

Kount has taken a unique approach to identity trust that puts the customer at the center of the transactions, not just their transactions’ risk score. By capitalizing on the insights gained from their Identity Trust Global Network, Kount can use AI and machine learning algorithms to deliver personalized responses to transaction requests in milliseconds. Using both unsupervised and supervised machine learning algorithms and techniques, Kount can learn from every customer interaction, gaining new insights into how to fine-tune identity trust for every customer’s transaction.

In choosing to go in the direction of identity trust in its product strategy, Kount put user experiences at the core of their platform strategy. By combining adaptive fraud protection, personalized user experience, and advanced analytics, Kount can create a continuously learning system with the goal of fine-tuning identity trust for every transaction their customers receive. The following graphic explains their approach for bringing identity trust into the center of their platform:

Putting Customers & Their Experiences First Is Integral To Succeeding With Identity Trust

How To Redefine The Future Of Fraud Prevention

 

Improving customer experiences needs to be the cornerstone that drives all fraud prevention product and services road maps in 2020 and beyond. And while all fraud prevention providers are looking at how to reduce friction and improve customer experiences with fraud scoring AI-based techniques, their architectures and approaches aren’t going in the direction of identity trust. Kount’s approach is, and it’s noteworthy because it puts customer experiences at the center of their platform. How to redefine the future of fraud prevention needs to start by turning trust into a sales and customer experience accelerator, followed by designing in identity trust. Hence, it’s the foundation of all customer experiences. By combining the power of networked data and adaptive AI and machine learning, more digital businesses can turn trust into a revenue and customer experience multiplier.

How AI Is Improving Omnichannel CyberSecurity In 2020

How AI Is Improving Omnichannel CyberSecurity in 2020

  • 52% of financial institutions plan to invest in additional measures to secure existing accounts, and 46% plan to invest in better identity-verification measures.
  • 42% of digital businesses that consider themselves technologically advanced are finding fraud is restraining their ability to grow and adopt new digital innovation strategies.
  • 33% of all businesses across retail, financial institutions, restaurants, and insurance are investing in their omnichannel strategies this year.

These and many other insights are from Javelin Strategy, and Research report published this month, Protecting Digital Innovation: Emerging Fraud and Attack Vectors. A copy of the report can be downloaded here (25 pp., PDF, opt-in). The methodology is based on a survey of 200 fraud and payment decision-makers for businesses headquartered in the United States. Respondents are evenly distributed from four industries, including consumer banking, insurance, restaurants/food service, and retail merchants.

The survey’s results are noteworthy because they reflect how AI and machine learning-based fraud prevention techniques are helping retailers, financial services, insurance, and restaurants to reduce false positives that, in turn, reduces friction for their customers. All industries are in an arms race with fraudsters, many of whom are using machine learning to thwart fraud prevention systems. There are a series of fraud prevention providers countering fraud and helping industries stay ahead. A leader in this field is Kount, with its Omniscore that provides digital businesses with what they need to fight fraud while providing the best possible customer experience.

The following are the key insights from the Javelin Strategy and Research report published this month:

  • Retailers, financial institutions, restaurants, and insurance companies need to invest in fraud mitigation at the same rate as new product innovation, with retail and banking leading the way. Restaurants and insurance are lagging in their adoption of fraud mitigation techniques and, as a result, tend to experience more fraud. The insurance industry has a friendly fraud problem that is hard to catch. Over half of the financial institutions interviewed, 52% plan to invest in additional technologies to secure existing accounts, and 46% plan to invest in better identity-verification measures. Based on the survey, banks appear to be early adopters of AI and machine learning for fraud prevention. The study makes an excellent point that banking via virtual assistants is still nascent and constrained by the lack of information sharing within the ecosystem, which restricts authentication measures to PINs and passwords.

How AI Is Improving Omnichannel CyberSecurity in 2020

  • 57% of all businesses are adding new products and services as their leading digital innovation strategy in 2020, followed by refining the user experience (55%) and expanding their digital strategy teams. Comparing priorities for digital innovation across the four industries reflects how each is approaching their omnichannel strategy. The banking industry places the highest priority on improving the security of existing user accounts at 52% of financial institutions surveyed. Improving security is the highest priority in banking today, according to the survey results shown below. This further validates how advanced banking and financial institutions are in their use of AI and machine learning for fraud prevention.

How AI Is Improving Omnichannel CyberSecurity in 2020

  • Digital businesses plan to improve their omnichannel strategies by improving their website, mobile app, and online catalog customer experiences across all channels in addition to better integration between digital and physical services is how. 40% of respondents are actively investing in improving the integration between digital and physical services. That’s an essential step for ensuring a consistently excellent user experience across websites, product catalogs, buy online and pick up in-store, and consistent user experiences across all digital and physical channels.

How AI Is Improving Omnichannel CyberSecurity in 2020

  • 69% of all digital businesses interviewed are planning to make additional fraud investments this year. Banking and financial institutions dominate the four industries surveyed in the plans for additional fraud investment. 82% of consumer banks are planning to invest in additional fraud detection technologies. Insurers are least likely to invest in fraud detection technologies in 2020. The study notes that this can be attributed to insurers’ unique challenges with first-party fraud or fraud committed by legitimate policyholders, which is poorly addressed by many mainstream fraud controls.

How AI Is Improving Omnichannel CyberSecurity in 2020

  • Using AI-based scoring techniques to detect stolen credit card data being used online or in mobile apps, dominates financial institutions’ priorities today. 34% of financial institutions cite their top fraud threat being the use of stolen credit card data used online or in mobile apps. 18% say account takeovers are their most important area to reduce fraud. Financial institutions lead all others in fraud technology investments to thwart fraud, with managing digital fraud risk being the highest priority of all compared to the three other industries represented in the survey.

How AI Is Improving Omnichannel CyberSecurity in 2020

  • 52% of all financial institutions say that improving the security of existing user accounts leads all digital investment priorities in 2020. What’s significant about this finding is that it outpaces adding new digital products and services and improving identity verification of new users. This is another factor that contributes to financial institutions’ leadership role in relying on AI and machine learning to improve fraud detection and deterrence.   

How AI Is Improving Omnichannel CyberSecurity in 2020

 

 

AI Is Predicting The Future Of Online Fraud Detection

Bottom Line: Combining supervised and unsupervised machine learning as part of a broader Artificial Intelligence (AI) fraud detection strategy enables digital businesses to quickly and accurately detect automated and increasingly complex fraud attempts.

Recent research from the Association of Certified Fraud Examiners (ACFE)KPMGPwC, and others reflects how organized crime and state-sponsored fraudsters are increasing the sophistication, scale, and speed of their fraud attacks. One of the most common types of emerging attacks is based on using machine learning and other automation techniques to commit fraud that legacy approaches to fraud prevention can’t catch. The most common legacy approaches to fighting online fraud include relying on rules and predictive models that are no longer effective at confronting more advanced, nuanced levels of current fraud attempts. Online fraud detection needs AI to stay at parity with the quickly escalating complexity and sophistication of today’s fraud attempts.

Why AI is Ideal for Online Fraud Detection

It’s been my experience that digitally-based businesses that have the best track record of thwarting online fraud rely on AI and machine learning to do the following:

  • Actively use supervised machine learning to train models so they can spot fraud attempts quicker than manually-based approaches. Digitally-based businesses I’ve talked with say having supervised machine learning categorize and then predict fraudulent attempts is invaluable from a time-saving standpoint alone. Adopting supervised machine learning first is easier for many businesses as they have analytics teams on staff who are familiar with the foundational concepts and techniques. Digital businesses with high-risk exposure given their business models are adopting AI-based online fraud detection platforms to equip their fraud analysts with the insights they need to identify and stop threats early.
  • Combine supervised and unsupervised machine learning into a single fraud prevention payment score to excel at finding anomalies in emerging data. Integrating the results of fraud analysis based on supervised and unsupervised machine learning into one risk score is one way AI enables online fraud prevention to scale today. Leaders in this area of online fraud prevention can deliver payment scores in 250 milliseconds, using AI to interpret the data and provide a response. A more integrated approach to online fraud prevention that combines supervised and unsupervised machine learning can deliver scores that are twice as predictive as previous approaches.
  • Capitalizes on large-scale, universal data networks of transactions to fine-tune and scale supervised machine learning algorithms, improving fraud prevention scores in the process. The most advanced digital businesses are looking for ways to fine-tune their machine learning models using large-scale universal data sets. Many businesses have years of transaction data they rely on initially for this purpose. Online fraud prevention platforms also have large-scale universal data networks that often include billions of transactions captured over decades, from thousands of customers globally.

The integration of these three factors forms the foundation of online fraud detection and defines its future growth trajectory. One of the most rapid areas of innovation in these three areas is the fine-tuning of fraud prevention scores. Kount’s unique approach to creating and scaling its Omniscore indicates how AI is immediately redefining the future of online fraud detection.

Kount is distinct from other online fraud detection platforms due to the company’s ability to factor in all available historical data in their universal data network that includes billions of transactions accumulated over 12 years, 6,500 customers, across over 180 countries and territories, and multiple payment networks.

Insights into Why AI is the Future of Online Fraud Detection

Recent research studies provide insights into why AI is the future of online fraud detection. According to the Association of Certified Fraud Examiners (ACFE) inaugural Anti-Fraud Technology Benchmarking Report, the amount organizations are expected to spend on AI and machine learning to thwart online fraud is expected to triple by 2021. The ACFE study also found that only 13% of organizations currently use AI and machine learning to detect and deter fraud today. The report predicts another 25% plan to adopt these technologies in the next year or two – an increase of nearly 200%. The ACFE study found that AI and machine learning technology will most likely be adopted in the next two years to fight fraud, followed by predictive analytics and modeling.

PwC’s 2018 Global Economic Crime and Fraud Survey is based on interviews with 7,200 C-level and senior management respondents across 123 different nations and territories and was conducted to determine the true state of digital fraud prevention across the world. The study found that 42% of companies said they had increased funds used to combat fraud or economic crime. In addition, 34% of the C-level and senior management executives also said that existing approaches to combatting online fraud was generating too many false positives. The solution is to rely more on machine learning and AI in combination with predictive analytics as the graphic below illustrates. Kount’s unique approach to combining these technologies to define their Omniscore reflects the future of online fraud detection.

AI is a necessary foundation of online fraud detection, and for platforms built on these technologies to succeed, they must do three things extremely well. First, supervised machine learning algorithms need to be fine-tuned with decades worth of transaction data to minimize false positives and provide extremely fast responses to inquiries. Second, unsupervised machine learning is needed to find emerging anomalies that may signal entirely new, more sophisticated forms of online fraud. Finally, for an online fraud platform to scale, it needs to have a large-scale, universal data network of transactions to fine-tune and scale supervised machine learning algorithms that improve the accuracy of fraud prevention scores in the process.

%d bloggers like this: