Author: Clari5
An Innovative Approach to Loan Early Warning System
Given the slackening pace of growth preceded by a spike in quantitative easing and flush liquidity in many countries, severely impacted corporate borrowers’ debts servicing, and consequently, there’s a higher potential for loan defaults. This whitepaper examines critical early warning indicators and scenarios, why multidimensional inputs are crucial to LEWS efficiency and the need for an innovative approach to it.
Bank of Ceylon Now Live with Clari5 AML to Battle Sophisticated Financial Threats
Recognized as bankers to the nation and with global operations in Asia and the UK, Sri Lanka’s largest bank, Bank of Ceylon (BOC) is now live with Clari5 real-time Anti-Money Laundering solution for addressing money laundering threats. Read More
Clari5 Anti-Money Laundering & Watch List Monitoring capability featured in Chartis Research latest report on AML/WLM
Premier banking risk technology research firm Chartis has featured Clari5 in the Point Solutions quadrant in their latest report on AML/WLM. Point Solutions focus on precise component technology capabilities, addressing a critical need in risk technology by solving specific risk management problems with domain-specific software applications and technologies. Point solutions are known for being innovative, as their deep focus on a relatively narrow area creates thought leadership and intellectual capital Read More
Beating Scams with Smarts: Aiming for a Zero-Fraud Financial Ecosystem
Even as financial institutions implement more sophisticated fraud-mitigation techniques, they have not been keeping pace with criminals. A study by ISMG during fall 2018, to gauge fraud’s evolution and the impact of emerging technology, surveyed 150 financial institutions (primarily in the US), of which 37% had assets under management of $2bn or more.
79% said the number of fraud incidents has remained steady or increased over the past year, while 70% said financial losses from these incidents have also stayed steady or increased.Top forms of fraud were Payment card fraud at 56%, ACH/wire fraud at 49% and phishing (non-business email compromise) at 44%.
When asked about the biggest barrier to improving fraud prevention, 23% said their controls don’t speak with one another and that they don’t want to add any new anti-fraud controls that would impact customer experience. 33% believed technologies like artificial intelligence, machine learning and data analytics have high capability to detect / prevent fraud.
Despite complex processes and procedures in place, the reasons for continued fraud incidents are many. They range from lack of due diligence, inadequate auditing and lack of stringent checks and balances and anti-fraud technology from a bygone era. Meanwhile, sophisticated fraudsters nimbly change strategies to evade detection, even as the quantum of data generated daily by banks becomes more and more massive to sift through.
While banks are doing their best to further tighten their controls, processes and various audits (such as statutory audit, risk-based internal audit, concurrent audit, information systems audit and special audits), they also need to equally importantly consider some of the key technologies available to combat the menace.
Machine Learning
Being able to use ML to spot shifting patterns can form a vital part in improving detection rates while eliminating false positives.
While AI and ML are closely related, there are a few key differences. AI is the ability of a machine to perform actions without human intervention, while ML refers to a particular approach to AI that can take data and algorithms and apply it to new scenarios and patterns without being programmed directly.
AI can mimic actions it has either seen or been previously taught, without any new intervention, and is used to perform a range of specific tasks. Applied AI has been around for a while, for activities like auto-trading stocks based on a predefined set of rules, identifying/sorting images, or even playing chess.
ML is an extension of AI and is the next level in the evolution of the technology. The key characteristic of an ML algorithm is its ability to ingest large volumes of data and ‘learn’ for itself how to apply its knowledge to future scenarios.
This does not mean that ML is the only option for fraud detection use cases. For specific scenarios, where banks are looking for a narrowly-defined set of parameters, or reacting to a new fraud vector, using rules can be the answer for fraud prevention in real-time.
ML meanwhile is better-equipped to deal with spotting evolving patterns and reacting without instruction or human intervention. In fraud detection, AI can monitor the transaction patterns of a customer and send out an alert if it spots a deviant transaction.
With ML, the system can recognize more comprehensive changes in behaviors and bring in data from elsewhere to build its understanding of what a fraudulent transaction looks like without human influence.
Neural Networks
Neural network technology was born from the need to have an artificial system that could perform “intelligent” tasks similar to those shown by the human brain. The inherent nature of neural networks is the ability to learn and being able to capture and represent complex input/output relationships.
Neural networks resemble the human brain because it acquires knowledge through learning and its knowledge is stored within inter-neuron connection strengths (or synaptic weights).
Traditional linear models are inadequate when it comes to modeling data that contains non-linear characteristics. The real strength of a neural network lies in its ability to represent both linear and non-linear relationships and in their ability to learn these relationships directly from the data being modeled.
Fraud Analytics
Various rule-based anomaly detection methods are already being used by many banks, but they have their limitations. Fraud detection capabilities are vastly enhanced with analytics, giving a whole new dimension to fraud detection techniques.
-
- Hidden pattern recognition – Fraud analytics helps identify scenarios, new trends and hidden patterns under which frauds occur. Traditional methods miss out on these aspects.
-
- Data integration – Fraud analytics combs through data and combines data from multiple sources including public records and integrates it into a model.
-
- Enhances existing efforts – enhances traditional rule-based methods instead of replacing them.
-
- Harnessing unstructured data – Deriving value from unstructured data is an unexplored goldmine and fraud analytics helps achieve this. In most banks, structured datais stored in data warehouses. Unstructured data is where there’s a high chance for fraudulent activity to occur. Text analytics plays a key role in reviewing this data and preventing fraud.
-
- Fraud analytics along with performance measurement helps to standardize, maintain control and enables continuous improvement.
Entity Link Analysis with Graph Database
Relational databases require datasets to be modeled with sets of tables and columns. By carrying out a series of complex joins and self-joins, rings in such scenarios can be uncovered.These queries complex to build, expensive to run and pose significant technical challenges on scaling. The full extent of this problem becomes apparent as we imagine the exponential explosion that occurs as the ring grows along with the total dataset.
Graphs are designed to convey relationships between data and can help uncover patterns that are difficult to detect using traditional representations like tables. Since they are designed to query intricately connected networks, the graph databases can be used to identify fraud rings in a fairly straightforward manner.
Social Network Analysis (SNA)
The scope of SNA is beyond just social media.The social network is a network of entities connected in a particular fashion. The entities include credit cards, companies, merchants and fraudsters. This can include IP address information, geospatial data, online transactions, and banking data, social media data, call behavior data and other forms of transactional data.
All such data is often stored in unstructured formats in telecom registries, social media, payment gateways or bank servers. There are methods to probe such large networks of relationships and establish suspicious patterns of behavior through graph database technology that has been specifically developed to work with big datasets.
Storing and retrieving interconnected information in a native ‘network graph’ format can deliver interactive network visualizations that identify links in transaction chains, discover hidden structures, locate clusters and patterns, and apply specialized algorithms to identify suspicious patterns.
Advanced analytics methods such as ML are already applied to detect fraudulent transactions. Along with such analytical methods, SNA with graph databases can significantly reduce the false positive ratio in fraud detection.
Fuzzy Logic
Fuzzy logic is a method of analyzing financial and non-financial statement data. When applied to fraud detection, a fuzzy logic program clusters information into various fraud risk categories. These clusters identify variables that are used as input in a statistical model.
Expert reasoning is then applied to interpret responses to questions about financial and non-financial conditions that may indicate fraud. The responses provide information for variables that can be continuously developed over the life of the bank.
Continuous monitoring of unstructured data helps analyze sentiments, tones, and elements such as incentive, pressure, and rationalization. Fuzzy logic along with SNA can reveal threats of possible collusion.
In Summation
There’s no panacea yet to have a zero-fraud scenario but implementing stricter checks and measures with a layered approach plus architecting and activating an advanced real-time defense framework that harnesses an ideal blend of relevant best of breed technology, helps take a bank’s anti-fraud strategy to the next level.
References
- 5 Tips to Reduce Banking Fraud – Bank Info Security
- How to Start Using AI to Combat Money Laundering – Bobsguide
- Using AI to Fight Fraud and Money Laundering – Diebold Nixdorf Blog
- Cybercrime Damages $6 Trillion By 2021 – CybersecurityVentures
March 2019 Issue
Clari5 is Winner of ISPMA Product Excellence Award, 2019
The International Software Product Management Association (ISPMA) is an open non-profit association of experts, companies and research institutes with the goal to foster software product management excellence across industries. The SPM (Software Product Management) Excellence Awards celebrate excellence in software management practices and showcase best practices and role models. At a grand ceremony at the IIM Bangalore which was attended by senior representatives from industry, academia and information technology, Clari5 bagged the SPM Excellence Award for innovation, maturity of SPM practices and business performance. Read More
Cisco India & SAARC Partner Confluence 2019
Cisco India & SAARC Partner Confluence 2019
4-6 February, 2019
Manama, Bahrain
The 3-day partner conference had Cisco’s India & SAARC leaders and CXOs of partner organizations converging to debate the opportunities in digital transformation. CustomerXPs participated in the discussion ‘Digital Disruption: Monetizing the Opportunity’ which debated the mindset shift required to be successful in digital; what digital disruption actually means for organizations; expected customer outcomes in financial services and the challenges in executing digital transformation.
Chartis Research mentions CustomerXPs as ‘Best-of-Breed’ Vendor in the ‘AI in Financial Services, 2019’ Report
Chartis Research has recognized CustomerXPs as a best-of-breed vendor in the premier research firm’s latest ‘Artificial Intelligence in Financial Services, 2019’ Report. We are featured in the RiskTech Quadrants for Analytics and for Packaged Applications. This is a recognition of a best-in-class AI/ML solution that can capture a significant market share in the market their Quadrants address. Additionally, it recognizes a strong client base, a sustainable strategy and invest heavily in R&D. Read More
Banking on RPA to Combat Financial Fraud
The volley of financial services offered to and engaged by a common man today demands sophisticated systems to collect and connect their data. Regulatory compliance and customer due diligence carve out the biggest chunk of a financial firm’s time and resources: on an average, $60 million[1] per firm per year. Robotic process automation in banking has the potential to overhaul these processes and replace them with time- and cost-effective workflows. It streamlines the communication between disparate bank systems to create a holistic financial footprint of the customer while reducing effort and expenditure.
Although RPA has existed inconspicuously in many banking processes, it enters its renaissance with the help of Machine Learning (ML), Natural Language Processing (NLP) and Artificial Neural Networks (ANN). Together, these technologies constitute the broad domain of Artificial Intelligence (AI). They drive human-like operations without much intervention from employees in the repetitive tasks. The re-invented RPA is likely to become the core of most bank fraud-detection and customer experience processes in the present market.
Clari5, the ML-driven cross-channel enterprise financial risk management suite, leverages RPA-integration to automate risk assessment and fraud investigation solutions end-to-end. It can pull data from multiple channels (Credit, debit, loan, mortgage etc.) in real-time and trigger instant alerts to manage cases with minimal human oversight.
In a preemptive effort to fight financial crime, larger banks are opting to use such automatedmulti-jurisdictional platforms to pull customer information from all service lines, rather than creating yet another silo for technology. And RPA is the enabler behind this evolved strategy.
The Concept: Fin-bots and their ‘Brains’
Contrary to popular belief, RPA doesn’t mean assigning the corner office to RoboCop and saving on his (or its?) employee benefits. The ‘Robot’ in robotic process automation refers to a software bot that automates certain tasks that are too monotonous and mundane for the human mind. It’s equipped with a conceptual ‘brain’ that ‘learns’ the procedure programmed into it. It’s akin to reading a book and following the instructions to the letter except the bots can do it faster, cheaper and without human error.
With the advent of Artificial Intelligence aided by machine learning, these bots are further granted with cognitive capabilities that enable judgment-based actions.ML facilitates automatic learning and improvement in such intelligent systems. Bots learn by analyzing known or unlabeled datasets. They use their inbuilt learning algorithm to create models and make predictions about the output values of the datasets.In banking, this gives the bots greater autonomy and reduces the need for human supervision through the course of recognizing alerts, collecting customer data, credit scoring, and subsequent fulfilment activities. While they would still require some human touchpoints in the process, they can resolve issues with modelized data just like a human would.
NLP takes the capabilities of these bots to the next level by coaching them to decode unstructured datasets like free-form text. The combination of NLP and ML helps RPA-integrated bank fraud detection systems to capture customer data from multiple avenues, evaluate it, convert it to an actionable form and dispose it to concerned teams. Artificial Neural Networks simulate the human brain and are an advanced tool to upskill the fin-bots.
Integrating RPA into banking involves ‘training’ these software bots to perform tediousevidence-gathering tasks involved in tracking and flagging fraudulent activities. The resultant processes can be semi-automated or fully automated. To determine the extent of integration required, the manual proceduresinvolved must be analyzed. This helps firms recognize the high-volume, low-value actions. These actions can be coded into ‘if-then’ scenarios with minimal deviations and complemented by error-handling capabilities. In short, a software bot takes them over.
Pitting RPA against Bank Fraud
While there are plenty of uses cases, robotic process automation makes the most sense in a field like enterprise financial crime management. Firms now proactively monitor suspicious activity and enforce strict regulations to prevent financial fraud which might harm their customers and their reputation. As almost 80-90% of the new services are availed by existing customers, it’s that much more important to map their past and current transaction patterns to predict future threats. And if there’s a way to speed up and ease the process, it’s worth exploring. Enter RPA.
Both bank fraud risk assessment and anti-money laundering operations demand data collection from multiple legacy systems.RPA engages the conditional if-then algorithm to collect the information from all silos and highlight the anomalies in a complete financial profile.
In the semi-automated scenario, the bot can beassigned with a list of actions that are triggered when the risk analyst or fraud investigator runs the program. This would automatically take screenshots of the relevant accounts/details and collate them for manual scrutiny. Or the task can be fully automated such that once triggered, it runs in the background for multiple instances and performs consequential actions like sending message alerts to the customer or disseminating information to relevant departments within the firm. This frees the employee to tackle high-value tasks and boosts their overall productivity.
The Pros
We looked into RPA as a positive addition to financial crime management services because of its multi-pronged benefits. It’s viable as a complete solution, from setup to end-customer usage. First off, integrating RPA into banking does NOT require additional core infrastructure or many upgrades. The cost of implementation is limited as opposed to upgrading a legacy system, which is both expensive and risk-ridden.
The main operational advantages are of time and cost savings. RPA-integrated suites are usually designed to be user-friendly to employees with little or no coding experience. These fin-bots shoulder the burden of repetitive tasks and drive the employee morale up. They enable the firms to hire only specialized FTEs while the bots function round the clock, 365 days and continue monitoring at all times. With automatic time stamping and meta-data, it’s easy to track the data provenance and sequence of their activity.
As with any software, the code of RPA systems is easy to update and align with the evolving regulations. This ensures that yourrisk detection strategies remain current.The scalability of RPA also plays well with the unified data mapping approach.
RPA Use Cases in Bank Fraud Detection
Bank of Ceylon became the latest Clari5 partner to recognize the impact of the silo-breaking technology. Robotic Process Automation is a veritable catalyst in this type of undertaking. It has both individual/firm-level impact and country-wide implications in terms of fighting financial terrorism. Two use cases of Clari5 that stand out are:
Use Case1: Intelligent Alert Disposition
Suites that operate using Intelligent Process Automation (RPA + ML) authorize their bots to access their case management systems. The entire process from login up to resolution can be delegated to these bots. They may access the configured alerts from a queue. Based on the information, they can retrieve client ID and PAN details. This would further trigger requests to get the credit scores from external portals. Based on this score the bot might make an unsupervised closure or forward the alert to the trading team.
Given the number of transactions and the wide array of parameters that affect customer activity, this will reduce the huge workload in terms of addressing inconsequential alerts. But it also ensures that the real fraudulenttransactions are instantly spotted from a diverse dataset.
Use Case2: Enhanced Due Diligence for Trade Monitoring
With nations taking the initiative for a risk-based approach to battle financial terrorism and money laundering, RPA-integrated, cross-channel software emerges as the go-to solution. RPA bots can screen and spot high-value transactions to beneficiaries in risk countries. The transaction itself can be evaluated for potential fraud by comparing Bill of Lading to the Letter of Credit. The bots can handle these critical situations with greater accuracy and no vested interests. In fact, with the extent of insight achieved through RPA, you can check the trades made against the suppliers’ actual line of business. Given their ability to digest disorganized information from various sources, they can handle exception cases better than human employees.
The Challenges
There aren’t any notable challenges in consolidating robotic process automation into financial fraud risk management. However, the extent of its utilization depends on its successful implementation. The setup requires extensive process knowledge, technical acumen, and regular monitoring to ensure that the system delivers.
RPA is a promising participant in the surging digital transformation of financial firms. As connectivity aids more fraudulent activities, RPA-integration can ensure that the enterprises always remain two steps ahead of such attempts.The reduced process times and higher efficiency gains are extra perks. Considering the bigger picture, the virtual workforce can give banks an unbeatable competitive advantage in the market.
References:
[1]Thomson Reuters, 2016 Know Your Customer Survey