fbpx

ML Platform & Fraud Detection Model for TInka

tinka logo

About Tinka

Tinka’s ambition is to be the preferred financial services partner for thousands of (web) stores across the Netherlands. Their portfolio includes financial products such as pay-later options, pay in instalments, and credits. Through their (web) store partners, they serve millions of shoppers in a responsible and secure way. This is accomplished thanks to their Credit Risk Management system which allows them to closely monitor the spending behavior of their customers so that products are used responsibly.

The Challenge

With around 2mln active shoppers and more than 90mln transactions per year, Tinka’s challenge is to process as many legitimate payments as possible without causing any user friction. In order to achieve that goal, they need help leveraging machine learning and AI capabilities to better know their customers, reduce risk, and ensure compliance with strict financial and regulatory standards.

All of this needs to be achieved while keeping with the client’s values of transparency and honesty. To be able to quickly adjust to changes in fraud and/or pay behavior, the models need to be easily retrainable. Moreover, model explainability is also an important factor for reducing bias and improving the prediction process.

The Approach

Together with the client, we set out to improve their data activation capabilities. To achieve that, we built an end-to end Machine Learning platform using AWS Sagemaker which would allow the client to prepare, build, train, and deploy high-quality ML models quickly and efficiently.

On top of that, we developed several easily-retrainable models for invoicing and we supported Tinka with building a fraud detection model. We also implemented explainability models to help them avoid black box situations. The models were built using XGBoost algorithms.

The Results

We built and deployed an innovative end-to-end Machine Learning platform using AWS Sagemaker, which allows the client to test and develop advanced AI and ML use cases. Next to that we built two cloud-native and retrainable invoice models and helped Tinka implement their own fraud detection model. The invoice models predict the probability of defaulting, while the fraud detection model predicts if a transaction is fraudulent.

Next to that, explainability was integrated into all the models both on local level (each transaction) and global level (which features are predictive of fraud according to the model). This way customers can also get an explanation if their pay-later option is declined and what drove the algorithm’s decision. The purpose of adding explainability models is to continuously improve the algorithm, avoid bias, and keep high level of accuracy.