This article is written by Nomentia
Artificial Intelligence (AI) and Machine Learning (ML) are two technologies that have been widely discussed in recent years. They offer a range of tools that are gradually being integrated into our personal and professional lives. These technologies are particularly useful in situations where there are many time-consuming and manual tasks. Or where there is a large amount of data to analyze. One such application is payment fraud detection. Before diving into the use of AI and ML in fraud detection, it is important to address them separately.
AI systems are designed to integrate vast amounts of data with intelligent algorithms. They mimic or simulate human-like actions and decision-making processes. AI can be utilized for various techniques like problem-solving, natural language processing, image recognition, reasoning, learning, and more. The technology functions in a way that collects data, processes it, and selects an algorithm. It trains a specific model, modifies the model’s parameters, and evaluates the results. This can then potentially be deployed in the real world. As it operates, AI typically uses feedback loops from its users to improve over time.
Machine learning is a form of AI that teaches a system to think in similar ways to humans, as it learns and improves based on previous experiences. Machine learning algorithms typically need little supervision because they are learning by themselves.
We usually distinguish between three techniques of machine learning:
Supervised ML algorithms are taught to make predictions or decisions primarily based on previous data patterns. Here, the ML learns based on already labeled data. So, input data needs to be categorized beforehand. So that the algorithm will use it as a benchmark to come to conclusions when analyzing new data.
In unsupervised ML, there is no need for labeled or categorized data. Instead, the algorithm tries to find patterns or relationships in the data without explicit guidance. Typically, the goal of unsupervised ML is to explore data and find clusters or relationships.
With reinforcement learning, you train the algorithms to make sequential decisions. In an environment with a reward or penalty feedback mechanism that it learns from to improve its subsequent decisions. Usually, no labeled data is available. The algorithm needs to learn from its own experiences and the feedback it receives.
AI refers to the simulation of human intelligence in machines that are programmed to mimic human-like actions and decision-making processes. AI encompasses as a wide range of techniques, including problem-solving, natural language processing, image recognition, and expert systems, among others. It aims to create systems that can perform tasks that typically require human intelligence. Tasks such as reasoning, learning, perception, and problem-solving.
Machine Learning is a subset of AI that focuses on developing algorithms. This enables computers to learn from and make predictions or decisions based on data. ML algorithms allow machines to improve their performance on a task through experience without being explicitly programmed for that task. It does so by using statistical techniques to enable computers to learn patterns and relationships from data and make decisions or predictions.
Recent research by PwC showed that 51% of organizations have experienced fraud in the past two years. A 20-year high compared to previous survey results. Fraud mainly impacted organizations in terms of financial losses. Respondents highlighted that many of them will require new, advanced technologies to tackle the issue. Some respondents also mentioned that fraud had more considerable consequences. Like operational disruptions or damage to the brand or customer loyalty. Ultimately, AI has the potential to assist businesses in maintaining a secure payment environment. Thus safeguarding a company’s customers, revenue, and reputation.
RESEARCH BY PWC SHOWED THAT 51% OF ORGANIZATIONS HAVE EXPERIENCED FRAUD IN THE PAST TWO YEARS — A 20-YEAR HIGH COMPARED TO PREVIOUS SURVEY RESULTS
PWC’S GLOBAL ECONOMIC CRIME AND FRAUD SURVEY 2022
With the rise in cybercrime and the evolving sophistication of financial threats, we’ve come to an era where humans cannot keep up with processing an abundance of data efficiently and securely. We can by no means compete with the speed and thoroughness of data interrogation that AI and ML can deliver today. As a result, we need to embrace and team up with such technologies. To support this view, a recent study by the Association of Certified Fraud Examiners revealed that 17% of organizations already leverage AI and ML to detect and prevent fraud, and 26% of organizations are actively planning to adopt fraud detection AI or ML in the next two years. On top of that, technology providers are now heavily investing in developing practical AI-driven solutions to tackle payment fraud.
These days, ML and AI can help you with fraud detection in various ways. Let’s focus on some of the main ways how organizations currently leverage the technologies and what the future may bring:
For example, AI and ML can streamline payment processes and enable faster risk identification in payables, receivables, and reporting. They can help manage exceptions or spot anomalies in large data sets based on previous patterns it has studied.
AI can analyze large datasets much faster than human beings, and it provides good insights and points to pay attention to. Faster analysis will also help speed up decision-making. Especially with more data than ever and little time to analyze, it will become essential to save time while deriving insights by leveraging tools like AI and ML.
AI can help automate essential but manual tasks such as data entry, reconciling payments, or generating reports. Minimizing manual processes, in turn, reduces the room for errors and fraud.
Reconciliation of payments is essentially comparing two data sets with each other and finding matches, which AI and ML are incredibly good at. Even when anomalies arise, you can train AI to handle them in pre-set ways.
Machine learning tools are great at uncovering complex relationships from data humans may overlook. Hence, it can provide quick and valuable insights that are potentially strategically important or can impact cash flow.
Any payment data can be screened based on benchmarking it with historical payment patterns to pinpoint out-of-the-ordinary payments faster.
In some cases, AI has been used to score payments by risk based on factors like locations, banks, sums, recipients, countries, previous behavior, and much more. This way, you can easily identify the payments with higher risk levels and make sure they’re safe.
The advantage of the learning capabilities of AI is that it can, over time, identify risks increasingly well. It allows new types of risks to be spotted that you previously may not have caught.
In a few cases, AI has been applied for account takeover detection. For example, if unusual payment behavior or account usage patterns occur, machine learning has the capability to recognize it and notify the right person or put a stop to it, limiting any further financial damage.
When integrated effectively, machine learning can analyze incoming invoices and identify out-of-the-ordinary, duplicate, mismatched amounts, or other indicators of fraud. With a large number of incoming invoices, this can help payable departments save time.
Master data is one of the biggest assets of companies, and AI can help maintain it to be in good health. For example, it can organize it by categorization, create links or connections between values, and clean up master data into more usable formats, to name a few. Better structured master data provides better insights and makes it easier to spot fraud.
You can let AI check future payments against historical payment data and establish certain tolerance levels and sensitivity for false positive management. Since dealing with false positives can be a lot of work for accounting, treasury, or finance, it can help speed up the process.
Suppose AI is connected to the internet or apps in real-time; it can deduce trends, market data, signals, and other external factors, providing insight into potential disruptions or risks at an early stage. There are various use cases for this. For example, it can help predict fraudulent attacks based on cybercrime trends, and it could even assist with considering the impact of fraud on cash flow in forecasts and help develop what-if scenario analyses.
AI is evolving rapidly, becoming more integrated with many apps and systems. In the future, it could be leveraged as a step-in-between systems for data checks, restructuring, reformatting, and other purposes to help speed up payment processes and minimize payment fraud.
AI is incredibly good at comparing data sets, which is exactly how sanctions screening works. Some payment technologies already offer sanctions screening, but AI has the potential to do so as well. This can be particularly helpful for teams that do not yet have a payment hub in place.
Perhaps in the future, payment hubs and TMS technologies will offer instructional functionalities like you’re already used to with ChatGPT, Google Bard, or Microsoft Copilot. Imagine all the questions you could ask based on all the data. Why did X payment not process? What is my exposure? How much do I have available on Y account? What caused the discrepancy between our budget and forecast?
While AI offers unprecedented opportunities for innovation and efficiency, it also raises various considerations that demand careful attention. Some of the things that we suggest you should at least consider:
Companies, banks, and financial technologies will likely incorporate new ways to leverage AI and ML technologies for fraud detection in the future. The true use of AI and ML was limited but is expected to develop rapidly. Recently, Euro finance hosted a webinar where some of the biggest companies explained how they leverage AI in treasury, finance, and accounting. It is definitely worth a watch if you are interested in how AI will shape the future beyond payment fraud.
By Alexander von Schirmeister,
CEO at Nomentia
A bank portal still works. The ERP still produces data. A spreadsheet still calculates a forecast. A payment approval workflow still moves from one person to the next. Reports still reach the CFO, even if they arrive later than expected. From the outside, treasury appears to function. Inside the process, finance teams know exactly how much effort is required to keep that appearance of control intact.
Modern treasury cannot rely on disconnected systems because the questions it needs to answer are no longer isolated. Cash visibility depends on bank data, account structures, ERP information, payments in progress, forecast inputs, intercompany flows, financing activities, and exposures. Liquidity planning depends on operational data from the business, but also on treasury assumptions, market conditions, working capital movements, and funding plans. Risk management depends on reliable exposure data, but also on trade execution, hedge documentation, limits, reporting, and accounting. If each part of this picture sits in a different place, the treasury team becomes the integration layer.
That integration work rarely surfaces. It lives in copy-and-paste routines, manual file checks, email reminders, reconciliation notes, spreadsheet tabs, and individual memory. It is also where most treasury management challenges quietly begin.
Disconnected systems create time loss because data has to be gathered before it can be analysed. They create duplicated work because teams maintain local trackers even when central tools exist. They weaken cash visibility because the latest view may depend on which bank file has arrived or which entity has responded. They weaken controls because exceptions are harder to identify when workflows are not connected.
The CFO does not usually see the process friction. The CFO sees the answer. If the answer is late, inconsistent, or hard to explain, confidence falls. Senior leadership needs reliable responses to simple but high-stakes questions: How much liquidity is available? Which cash flows are expected? Where is working capital tied up? Are internal payments efficient? Which exposures are material? Are guarantees, hedges, and commitments under control? These questions cannot be answered well when the data behind them has to be rebuilt every time.
The 2026 Nomentia Treasury and Cash Management report highlights that many treasury teams are in a transitional phase. They have moved beyond purely manual treasury, but still rely on multiple systems and partial automation. The pattern is familiar: the organisation has invested in technology, yet treasury still spends too much time reconciling information and validating reports. The issue is not that systems are missing. The issue is that they are not connected enough to support the pace of decision-making.
Disconnected systems are especially risky in three areas.
The first is visibility. If cash positions, transactions, forecasts, and payment statuses are not consolidated, treasury may see parts of the picture but miss the direction of movement. A balance report can show where cash is today, but it does not explain whether the position is temporary, restricted, exposed, or needed elsewhere in the group. Visibility without context can create false comfort.
The second is control. Treasury policies often look clear on paper, but control depends on how processes actually run. Who can approve a payment? Which entities have followed the forecast process? Which exposures have been validated? Which guarantee is close to expiry? Which hedge relationship needs attention? When workflows are disconnected, control becomes dependent on manual follow-up. That may work when volumes are low, but it becomes unreliable as banks, entities, instruments, and reporting expectations increase.
The third is decision speed. In volatile markets, delayed answers are not neutral. A late forecast can affect funding decisions. A delayed exposure view can affect hedge timing. A slow payment status check can affect supplier confidence. A late view of guarantees or credit line usage can affect working capital decisions. Treasury does not need real-time data for every decision, but it does need enough connected information to avoid making decisions with yesterday’s understanding.
A modern treasury management system should not be judged only by feature breadth. The more important question is how well it reduces the gaps between systems, data, workflow, and reporting. A strong setup connects bank information, ERP data, payment processes, cash forecasting, risk workflows, analytics, and audit trails into a reliable operating model. That does not mean every company needs every module at once. It means the architecture should support growth without forcing the team to rebuild its processes every time complexity increases.
Most people researching a TMS today will start with a web search or ask Copilot, Gemini, or ChatGPT. The answer they get back is usually a feature list. That’s not wrong, but it’s incomplete. A good treasury management system helps finance teams centralise cash, payments, forecasting, risk, controls, and reporting so they can make better liquidity and financial risk decisions with trusted data. Features are how it gets there. That’s the distinction worth keeping in mind when evaluating whether your current setup is still fit for purpose.
The path away from disconnected systems does not always require a large replacement project. In many organisations, the better approach is to identify the most painful manual bridges first. Where does treasury re-enter data? Where does the team wait for local input? Where do reports need manual explanation? Where are approvals outside the system? Where is the same number calculated in different ways? These questions show where fragmentation is creating the most business risk.
Connected systems create reliable answers. They reduce the manual work behind cash visibility, improve the quality of cash flow forecasting, and support stronger controls and compliance. They help the CFO understand not only what the numbers are, but what they mean for liquidity, risk, and action. Disconnected systems may still function. But they make treasury work harder than it should, and confident decisions harder than they need to be.
Treasury Masterminds is a community of professionals working in treasury management or those interested in learning more about various topics related to treasury management, including cash management, foreign exchange management, and payments. To register and connect with Treasury professionals, click the button below.
This article is written by TreasuryCube
In an increasingly complex financial environment, In-House Banks (IHBs) have emerged as a strategic imperative for corporations seeking enhanced cash visibility, optimized liquidity, and streamlined intercompany transactions. Drawing insights from a recent presentation by experts at Citi and seasoned treasurers, let’s explore what makes an IHB not just an option, but a cornerstone of modern treasury management.
An IHB is a centralized internal financial entity that manages cash, investments, foreign exchange exposures, and intercompany lending on behalf of corporate subsidiaries. Acting as a “virtual bank” for the organization, it reduces the volume of external banking transactions and provides critical advantages in cash management, governance, and compliance.
Importantly, an IHB is not a regional treasury center, shared service center, re-invoicing hub, or physical licensed bank. It’s a bespoke solution that integrates deeply with corporate finance operations.
An IHB addresses several core challenges that treasurers face:
Real-world IHB implementations, like those led by Brook Ballard at Oceaneering, showcase the tangible benefits:
Intercompany netting further reduces payment transactions, bank fees, and FX costs by consolidating cross-border intercompany settlements.
While beneficial for many, IHBs are particularly advantageous for:
At TreasuryCube, we recognize that the modern treasury is not just about managing cash, it’s about unlocking strategic value. An effective IHB is a critical tool to help achieve that vision, especially when supported by integrated technology, skilled people, and proactive governance.
Treasury Masterminds is a community of professionals working in treasury management or those interested in learning more about various topics related to treasury management, including cash management, foreign exchange management, and payments. To register and connect with Treasury professionals, click the button below.
This article is written by our partner, FIS
The reality of payment fraud has shifted from a question of whether an attack will occur to a growing likelihood of when and how it will occur.
For finance and treasury leaders, the strategies that provided a sense of security a few years ago may be insufficient against a new breed of sophisticated and relentless criminals. A 2024 survey from the Association for Financial Professionals underscored this reality, revealing that a staggering 79% of organizations were victims of payment fraud attacks or attempts.
This is not a distant risk: It’s an active, daily threat that demands a fundamental change in an institution’s defensive posture. The traditional, reactive approach – detecting and responding to fraud after it occurs – is, in many cases, no longer a viable strategy. The time has come to build a proactive defense.
Today’s fraudsters are often not lone actors but organized, well-funded operations that use advanced technology and psychological tactics. They study organizational structures, identify process gaps and exploit the path of least resistance.
Business email compromise remains a dominant method, where criminals impersonate executives or vendors with alarming authenticity to redirect funds. We’re also seeing the rise of AI-powered deep fakes, where a trusted voice on a conference call can be convincingly spoofed to authorize a fraudulent transfer.
These criminals understand that the entire payment lifecycle, from the initial onboarding of a vendor to the final reconciliation, presents a landscape of opportunity. They target the seams in your processes, exploiting the very human desire for efficiency and speed. This “disharmony,” a term coined by a FIS® and Oxford Economics study, captures the friction between the drive for growth and the drag of persistent security threats.
According to the study, 75% of C-suite executives identify fraud as a critical challenge.
How can organizations overcome the evolving threat of fraud? The answer lies in shifting from a fragmented, manual and reactive stance to an integrated, automated and proactive one.
A truly effective defense begins by fortifying the most common entry points. The vendor master file, for instance, is the heart of the payables process and a prime target. A single fraudulent change to a supplier’s bank details can lead to catastrophic losses before anyone realizes an error has occurred.
Overcoming this type of threat typically requires more than just diligence: It often demands a standardized, technology-enforced process. It includes implementing out-of-band verification, such as a phone call to a preverified contact, for any change to payment instructions. It means moving beyond trust and implementing strict, automated validation protocols.
As transaction volumes grow, manual reviews can become an impossible bottleneck, creating the very noise that criminals use to hide their illicit activities. This is where modern solutions like AI-assisted anomaly detection become increasingly indispensable.
Unlike static, rule-based systems that can only catch what they are programmed to look for, AI and machine learning establish a baseline of “normal” payment behavior for each vendor and transaction type. These systems operate in real time, analyzing payments for subtle deviations in amount, frequency or timing that would be difficult for the human eye to detect. When an anomaly is detected, the payment is automatically flagged for investigation before it leaves the organization. This preemptive capability is a game changer.
Organizations can achieve a greater level of control by consolidating their payment flows through a centralized payment hub. Instead of managing disparate security protocols across multiple ERPs and bank portals, a payment hub provides a more unified point of visibility and control.
A payment hub enables the consistent application of security policies, approval workflows and fraud detection analytics across the entire enterprise. It standardizes an institution’s defense, creating a fortress rather than a series of disconnected fences. A payment hub integrated with a third-party account validation service provides another critical layer, confirming that a beneficiary’s name matches their account information before a payment is ever initiated.
Reduce fraud risk and strengthen controls with FIS Payment Hub – Enterprise Edition
The path forward for finance and treasury leaders requires a strategic pivot. It means recognizing that fraud prevention is not merely a compliance checkbox but a strategic enabler of business resilience and growth.
Building a proactive defense involves a holistic approach that integrates advanced technology, standardized processes and a culture of vigilant verification. By embracing AI-driven monitoring, centralizing payment operations and empowering employees with specialized training, you can transform your security posture from reactive to preemptive.
This shift does not just mitigate risk: It builds the confidence and operational integrity necessary to thrive in a complex financial world.
Treasury Masterminds is a community of professionals working in treasury management or those interested in learning more about various topics related to treasury management, including cash management, foreign exchange management, and payments. To register and connect with Treasury professionals, click the button below.
