2021.AI protects public transport operator against cybercrime

AI proved the interlinkage between fraudulent transactions to save costs and protect a public transport operator against cybercrime

INDUSTRY: TRANSPORTATION & LOGISTICS

With instances of cybercrime on the rise, most organizations are subject to experiencing its effects. 2021.AI assisted this public transportation operator in recovering millions by connecting the dots between various fraudulent transactions.

Fraud prediction for a public transport operator

Cybercrime is a fast-growing epidemic. Both governments and businesses are increasingly faced with pressure from criminals exploiting the speed, convenience, and anonymity of the Internet to commit various types of crimes. Research from Cybersecurity Ventures projected that by 2021, cybercrime will have cost the world nearly $6 trillion.

This client case explains how a European public transportation operator used AI to identify and track thousands of transactions, numbers, and dates to scientifically analyze and link fraudulent transactions of organized cybercrime. The company is one of the largest public transport operators in Scandinavia, operating several modes of passenger transportation, covering both private and business customers.

The challenge

For several years, the operator searched for a way to document a pattern of fraudulent behavior in purchases of its online products, which cost them millions in euros each year. The operator knew that they were being attacked by organized cybercrime as they previously tracked suspicious transactions and credit card numbers manually. The challenge lied in finding a link between these single transactions to prove a pattern in online purchases from various suspicious purchasers that acted similarly.

Without being able to scientifically prove the patterns and linkages between the fraud cases, the financial costs could not be covered under the operator’s insurance policy. According to the insurance policy, only fraud cases above a certain threshold – more than €100.000 – could be filed and covered. The fact that the company’s products are split into multiple small transactions ranging from €5 to €600 created an issue with the insurance policy. Although these were proven acts of fraud, the amount fell far below the threshold. The operator needed to find a solution that could show the connection between the transactions and the profiles that committed the fraud, to prove that the total monetary amount was far more.

“It was a huge challenge for us to find a method that proved the interlinkage of fraudulent transactions that were necessary to get coverage from the insurance company. Especially considering the number of fraud cases that we are dealing with.” – Senior VP

The client and 2021.AI worked together to:

$

Scientifically prove collusion for fraudulent transactions

$

Apply AI models to identify patterns in the data

$

Report the model results together with known facts about the business

$

Present a scientifically-backed claim linking fraudulent transactions in front of the insurance company

The solution

The operator was able to make a breakthrough, solving this case by applying AI that could analyze thousands of transactions, numbers, dates, and more, to prove the interlinkage between the patterns of transactions and fraudulent behavior.

A series of AI models were built to search for hidden patterns in each transaction.

Because the operator already knew which transactions were fraudulent based on reportings from financial institutions, a classification model was built to show the significant differences between the fraudulent transactions and those that were non-fraudulent.

Then a clustering model was developed to define certain groups of behavior in fraudulent transactions. This model identified patterns in certain actions that could be grouped together.

The final model was a trained model, that could separate fraudulent and clean transactions and then identify multiple patterns in the fraudulent transactions, which could be linked to the different clusters.

“We have been working hard trying to solve these cases of fraud and tried multiple times to prove the cases to the insurance company, but we weren’t able to get there until we applied AI.” – Fraud Management

Three facts about the project

$

A public transport operator used machine learning to support arguments for insurance claims.

$

2021.AI collaborated with the operator’s fraud management team to create a series of models that linked fraudulent transactions.

$

The two organizations worked together to successfully recover several million in euros.

The results

With the ability to separate fraudulent transactions and identify the patterns, the organization proved the interlinkage between fraudulent behavior and specific profiles, saving the operator money and increasing its revenue and sales. Thanks to the models, the monetary numbers shown to the insurance company were above the threshold. The model results were presented in a comprehensive report which displayed the results, the assumptions, and applied methods, as well as the interpretation of the results, including inside knowledge from the internal fraud management team.

In the end, the client achieved its goal, successfully presenting the case to the insurance company, which resulted in coverage amounting to several million euros. The operator can now continue to spot and link fraudulent behavior in the future, which would be virtually impossible through a manual process.

Get in touch

Interested in taking AI into production and scale to every corner of your organization?