From detecting traffic obstacles for self-driving cars to recommending products, Machine Learning (ML) plays a key role in most organizations’ decision-making processes. For financial services organizations, machine learning is increasing critical in identifying risk, within consumer and corporate entities.
The Importance of Context
In the world of risk modeling, the input data points (or features) are particularly important – usually even more important than the choice of model or algorithm. In an industry with significant regulatory pressure for transparency and explainability in modelling, model choice is often restricted meaning the choice of input features can be the core reason for success (or failure) of the model. So, the key question is – how can we bring as much context into our features as possible?
Network based features provide an excellent way to inject a huge amount of information into your model, whilst keeping the required transparency and explainability One way of achieving this is by using bespoke document-entity networks to generate features describing how businesses and individuals are related to each other. At Quantexa, we’ve used network features describing relationships between companies and their directors as key inputs into our ML Shell Company detection model, which has resulted in a 20% uplift in performance compared to using just record-level features.
The model output – predicted shell companies and the agents creating them – has a range of applications for enhanced risk detection across AML (Anti-Money-Laundering), KYC (Know-Your-Customer), Credit Risk and Fraud.
Introducing Network Features
Networks can be used to model relationships between entities in many different circumstances. For example, networks of payments between parties can be used to find signs of financial crime. Searching for certain shapes in the network (e.g., cycles of similar sized payments) can lead to the detection of risks that would not have been identifiable by looking at transactions in isolation. If a list of known instances of financial crime is available, then network features such as the number of U-turn or cyclic payments can be used as part of a supervised learning model to enhance the prediction of future risks.
One obvious network to use as a basis for the modelling corporate risk is an organization’s legal hierarchy which includes its directors, shareholders, and subsidiaries. Simple characteristics such as the size of this network, the number (or density) of connections, and the number of layers can all be useful dimensions for segmentation or feature generation for supervised learning models.
The Power of Networks in Machine Learning
In the Quantexa ML Shell Company model, we have used a combination of features derived from organizations’ wider networks (including their legal hierarchies and director networks) and from company registry records. These network features include the identification of network shapes and patterns, as well as using techniques from graph analytics (including centrality analysis) to create new information about the entities in the network, like finding directors with a high importance in the network.

The director in the network has control of four organizations, all with single shareholders and based in profligate (or highly connected) addresses. Creating features such as ‘director’s company is based at a profligate address’ and ‘director shares directorship with a 100% shareholder’ can be very informative in finding shell companies. In addition, the director above has high ‘page rank’ (centrality) in the wider network.
These new network characteristics are used as features within a company level model. This evaluates if each company is likely to be a shell based not just on its own characteristics (size etc.) but also on this network context.
Including network features in the model significantly enhanced its performance and has so far led to the identification of over ten thousand new shell companies not identifiable from record-level models alone. The use of network features to provide context has added significant value in other areas too, including scorecard tuning, and even data quality analysis.
Unearthing More Complex Patterns
Recent research has uncovered a plethora of techniques for using networks as part of a machine learning lifecycle. In particular, the field of Graph Learning has evolved to use networks directly in machine learning algorithms (without creating summary features from the network). This will enable more complex patterns to be found in the networks which correlate with risk.
At Quantexa, we are actively pursuing how such techniques can apply in the field of risk modelling, where imbalanced classes, non-homogenous networks and sparse data are common challenges.
Kick-Start Your Journey to Supervised Machine Learning
Explore Quantexa’s AI & Analytics Methodology to unlock insight into building stronger AI and machine learning models.
You may be interested in…

How Banks Can Use Supply Chain Analytics To Enhance Client Experience
Learn how supply chain analytics transform the way banks extract value from customer data, enhancing dynamic decision-making across all operations.

Detecting & Preventing Scams with Advanced Analytics
Find out how banks can detect and prevent the growing problem of scams using advanced analytics – and how scams have evolved since COVID-19.

Overcoming Investment Fraud with New Technology Solutions
Since the infamous Bernard Madoff Ponzi scheme, financial institutions are turning to fraud detection tech to protect them. Find out why.

Data Decision Gap Risks Holding Back Economic Recovery, Global Research Finds
Learn how to close the data decision gap in the first-ever Data in Context report based on interviews with 750 IT and data decision-makers.

Top 30 Data & Analytics Predictions for 2022
Explore Quantexa’s top 30 data and analytics predictions for 2022 that every forward-thinking business leader should know about.
Related Solutions

Tax Authorities
Reduce the tax gap, identify fraud and non-compliance, and operate as efficiently as possible with limited resources.

Anti-money laundering
Reveal hidden risks and detect criminal activity faster. Reduce false positives to manage the cost of compliance. And improve investigations to make faster and more consistent decisions at scale.

Customs Agencies & Border Control
Contextual Decision Intelligence enables faster decisions, increased revenue collection and enhanced compliance. The Quantexa platform enables Customs and Border agency teams to analyze data successfully, automate and accelerate decision-making, and achieve improved results.

Fraud
Identify potentially fraudulent activity by looking at people or transactions in isolation. Understand the context surrounding the organizations you do business with to make fast, accurate decisions.

Fraud, Waste & Abuse
Empower your team with the best tools available for today’s challenges to identify and prevent fraud, waste and abuse with contextual decision intelligence software.

Credit Risk
Understand your customers, their business structures and supply chains. Make better lending decisions, faster. And support digital risk transformation.

Customer Intelligence
Generate a complete view of the context around your customers and prospects to build better relationships, reduce attrition and find hidden opportunities.

Revolutionize Your Financial Crime and Fraud Detection

Investigations
Enhance the efficiency, effectiveness and consistency of your operational and complex investigations to empower your teams to expose and understand risk faster.

Master Data Management
Connect all data—internal and third party—to create a joined-up, contextual view of all the relationships between your customers and every other domain.

Compliance
See how we help to reduce costs and improve coverage for financial crime compliance.

CDO
See how our platform uses contextual analysis to turn data into a high value asset.

CIO
See how our platform uses financial crime technology to enhance your existing IT ecosystem.

Healthcare
Reduce the tax gap, identify fraud and non-compliance, and operate as efficiently as possible with limited resources.

Contextual Monitoring
Reveal hidden risks and detect criminal activity faster. Reduce false positives to manage the cost of compliance. And improve investigations to make faster and more consistent decisions at scale.

Unified CRM Solution

Know Your Customer
Reduce significant manual effort across onboarding, refreshes and remediation. Automate checks, implement continuous monitoring, and focus on contextual decision making.

Growth and Retention

Contextual Engagement
Generate a complete view of the context around your customers and prospects to build better relationships, reduce attrition and find hidden opportunities.

Data Management
Connect all data—internal and third party—to create a joined-up, contextual view of all the relationships between your customers and every other domain.

Connected Customer View
Generate a complete view of the context around your customers and prospects to build better relationships, reduce attrition and find hidden opportunities.