The following Q&A occurred during the Everyday AI Conference in Paris.
At Bouygues Télécom, we get thousands of orders for our services daily. A few of them are fraud attempts, so we have to make sure that every order we accept is not fraud. We try to calculate some score to try to mitigate the risk. By discarding fraudulent commands, we bring great value to the company.
Dataiku was the main tool used to build the fraud detection model, make sure it was working, and validate it. We use Dataiku to retrain the model every month to ensure it remains valid and efficient in tracking every fraud reset attempt and ensure that we are only productionizing models that are better than the previous ones.
Orange has accelerated their data science practice with Dataiku, building a call load detection and triage model in just one month, with more use cases on the horizon.
Read moreThe issue of service downtime and failure (which can lead to significant revenue loss) is specifically prevalent amongst telcos, but this problem can be solved by using machine learning to predict what might cause service failures and prevent them from happening.
Learn MoreThough the savings generated by the express shipping recommendation model will only fully materialize over time, the tool when globally implemented is estimated to reduce express shipment costs by 11-36%.
Learn MoreBy empowering their employees and customers to use data for everyday decision making, SLB is reshaping the future of energy.
Learn More
