Home > Company News > Sports betting > Product & technology > PIN-UP.TECH creates its own ML/AI models to combat fraud in sports betting

PIN-UP.TECH creates its own ML/AI models to combat fraud in sports betting

| By iGB Editorial Team
Software specialist takes anti-fraud processes to a whole new level. Routine checks are now performed automatically, taking into account all available transaction data.

Effective risk management is one of the most important factors for success in the sports betting industry. Large volumes of data for each transaction require deep analysis in order to predict and subsequently prevent the possibility of fraudulent schemes, avoiding financial losses.

PIN-UP.TECH uses the latest technologies and tools to ensure the high quality, stability and security of its products, including the benefits of machine learning and artificial intelligence. ML/AI models have become one of the main tools within the new proprietary product of the PIN-UP team – a fully fledged anti-fraud platform. 

The approach of introducing machine learning and artificial intelligence into anti-fraud processes leads to a more advanced ability to summarise information, identify logic and patterns of customer behaviour, which is not available for methods such as manual analysis of transactions or the use of linear rules.

AI is an additional set of tools that helps the operations team work. It reduces the rate of errors and decision-making time in each specific case and opens up new knowledge about our clients. In some ways, AI even deepens the expertise of the specialists and broadens our horizons, since the models take a slightly different approach to decision making. Many tasks can already be given to AI offline. Thus, AI helps to scale, removes boring routine from daily operations and allows you to concentrate on a deeper analysis of other processes.

Decision-making models based on artificial intelligence analyse a huge number of parameters of each transaction including the frequency and size of bets, the selected events and their history. The model analyses lots of parameters, selects those with the highest predictive power and uses them in the forecast.

“For our task, machine learning models were used, the main one being the gradient extreme boosting model, which is one of the best for structured data. The essence of the method is to build an ensemble of models that consistently refine each other, thereby increasing the accuracy of the forecast,” said Volodymyr Todurov, chief analytics officer of PIN-UP Global.

The PIN-UP team’s plans include creating a whole arsenal of ML/AI models that will reduce the need for manual checks to a minimum and will be able to identify risky transactions with maximum accuracy.

PIN-UP.TECH is one of the areas of the international ecosystem PIN-UP Global, which develops software for the igaming industry and specialises in technological solutions. The direction creates high-quality products and also provides the PIN-UP ecosystem with infrastructure support.