Check supply chain risks with “transactional data”

VB - Controllare i rischi della filiera con i dati transazionali

We have seen how transactional data, the information about account movements, can provide a clear picture of the one’s financial health.

It is also important to understand the overall accounts’ health of firms or individuals, and to be able to prevent difficult situations. This is possible by aggregating individuals’ data and drawing indications about individual risks not easily deducible by limiting observation to the single current account.


Network analysis to keep an eye on the supply chain

Let’s take the case of a financial intermediary that provides companies credit services, operating with a specific territorial focus.

Now, from the transactional data emerges who-pays-who: the dependencies’ chain in the cash flows that describes the cascading money flow between customers and suppliers. These are companies that produce goods or services, but also consultants and professionals.

This relationship network made up of payments between A and B, with amounts, signs and dates, is the raw material from which, with our transactional data analysis solution, we are able to extract very valuable information for the financial intermediary.

Using the Network Analysis, we can capture this information and provide it in an intuitive and user-friendly way for the intermediary. The following graph represents the supply chain (we will call it “Chain X”): each dot represents a company, a small or a large one, connected to the others by lines that represent the money flows (and, on another level, goods and services).



At a first glance, we can see areas of higher density, that are real “hubs” in the supply chain, namely companies that are hot spots, as they are connected with many other companies, of which they are customers or suppliers. Now, let’s highlight the main hubs, those companies with the highest number of connections (“degrees”, in the Network Analysis language).



If these firms go in trouble, they could become a problem: they could generate a domino effect, a risk transmission within the business system on which the health of the financial intermediary’s business depends.


… and control systemic risk

These are, to all intents and purposes, systemic risk’s outbreaks, which would be difficult to grasp in their fullness by only looking at the individual firm. Instead, the aggregate analysis of transactional data, immediately brings these situations to light: Network Analysis enables the visualization and weighing of dependency relationships in the supply chain and the systemic risk tracking.

In this way, the risk manager (or other control functions) can quickly get an overview, which captures the “Big Picture”, and allows to monitor the situation, with particular attention to the most relevant potential outbreaks. In this way, you can prevent and contain the domino effect’s risk, whereby a bad payer has an impact on companies of which it is a client, causing a contagion effect (and similarly on the supplier side, for supply chain impacts). And all of this is done with up-to-date and timely information because it comes from transactional data, processed by reactive Machine Learning models and with great capacity of adapting to changing situations.

These are tools that can be used at various levels of the intermediary’s organization (management, branches), typically to supplement traditional credit models, or as a basis for defining next-generation risk models. But this is just one of the multitude of things that can be done using transactional data in aggregate.

The Virtual B solution

At Virtual B we believe that transactional data is very useful, and we are able to help you make the most of it. If this topic is interesting for you, contact us at the link below and find out how to increase the value of your data.

Contact us

Leave a Reply