Internship: Enhanced payment monitoring through probabilistic modelling

Description de l'offre

Join us and shape the future of travel

Shaping the future of travel has always been important to us at Amadeus. Today, with technology getting smarter by the minute, that future is more exciting than ever.

We work at the heart of the global travel industry. Amadeus offers you the opportunity to learn and grow and drive your own progression in an exciting and multicultural environment.

Our people are driven by a passion for 'Where next?' If you want to shape your career and the future of travel, Amadeus is the place for you.

Team description:

The team is responsible for developing and operating the Payment Hub (Amadeus Payment Platform). The Hub processes payments through credit card networks, acquiring banks or alternative methods of payment providers (e.g. Paypal) and provides a complete ecosystem of payment solutions.

One of the main objectives of Amadeus Payment Platform is to be flexible, meaning that our customers should be able to configure it at any time in order to choose the best payment partners for handling authorisation (payment approval) and capture (request for funds transfer). For instance, a customer could configure the platform in order to reduce fees based on the payment card issuing bank country, the card currency, the transaction amount, the total amount of all transactions sent to an acquirer during a month, etc...

However, flexibility comes with a cost! The risk of losing payments after a configuration update... Every enhancement in flexibility should be coupled with enhancement in the monitoring process in order to reduce any kind of risk affecting our customer’s revenue.

Main responsibilities:

The objective of this internship is to help the team to design and develop an offline Machine Learning process that would create a probabilistic model representing our production payment data. The probabilistic model would further be used by an offline monitoring process for raising alerts for transactions that are not coherent with the model output.

For instance, if inference on the probabilistic model shows that a transaction of 1000 EUR paid with a VISA ELECTRON card issued from a bank in Brazil has a probability of 99% to be redirected to payment partner A for authorisation and to payment partner B for capture.

However that actually it has been sent to payment partner C for authorization and not sent to any payment partner for capture an alert should be raised by the monitoring process applying the probabilistic model.

The trainee will participate in following activities:

• Provide a thorough state-of-the-art about techniques/algorithms/heuristics currently used for features extraction, features selection, unsupervised leaning, supervised learning.

• Design, implement and test the pre-processing of Amadeus Payment Platform data for features extraction and features selection.

• Implement and compare different processes of Machine Learning in order to choose the most adapted to our data and objectives.

• Implement a prototype capable of creating a probabilistic model allowing inference on new data coming from production environment.

Please note that in accordance with French law, internships require a school agreement and that the applicant must be a registered student until the end of the internship.

Any duplication and display of partial or full content of our job advertisement on any support, such as brochures, websites, mail, emails, this list is not exhaustive, is strictly forbidden without prior formal Amadeus’ authorisation.

Recruitment agencies:Amadeus does not accept agency resumes. Please do not forward resumes to our jobs alias, Amadeus employees or any other company location. Amadeus is not responsible for any fees related to unsolicited resumes.