Internship followed by CIFRE thesis with BPCE on "Machine Learning Algorithms and Explanations to Detect Banking Fraud"
Toulouse, France
il y a 2j

Description :

Machine Learning Algorithms and Explanations to Detect Banking Fraud

Context :

This internship is a collaborative project between BPCE group (Banque Populaire Caisse d'Epargne) and the artificial intelligence institute of Toulouse (ANITI).

It will be followed by a CIFRE thesis with the same partners .

The internship will be based in BPCE SA (member of the Communauté BPCE) in the Secrétariat Général department, which deals with compliance, legal, permanent controls, security, public relations, etc.

The team that will host the intern is called Intelligence Artificielle & Modèles and has for mission to develop AI systems (Machine Learning algorithms, data science studies, robotization of simple processes) for the benefit of the rest of the Secrétariat Général.

The academic partner is the Artificial and Natural Intelligence Toulouse Institute (ANITI) and in particular the group DeepLEVER (for Deep Learners Explanation and VERification), which aims at explaining and verifying machine learning systems via combinatorial optimization in general and SAT in particular.

Joao Marques-Silva and Emmanuel Hebrard will be the academic co-advisors. The intern will also have access to LAAS-CNRS to have regular meetings the academic supervisors.

Industrial Problem :

BPCE is interested in designing Machine Learning models, in particular to detect illegal activities such as fraud (involving checks, money transfers or card payments), dirty money laundering or terrorism financing.

Moreover, the models should satisfy a range of properties :

  • Because banking and insurance groups are accountable to authorities on the ethical aspects of such fraud detection systems, the model should be interpretable.
  • In particular, this rules out deep learning or other complex systems, and the focus will be on rule-based models (such as decision trees, decision lists, decision sets, etc.)

  • Datasets are often imbalanced since occurrences of illegal transactions are relatively rare. The chosen solution should therefore cope in some way with this caveat, for instance by using different loss metrics, or resampling when possible.
  • Fraudsters often adapt their behavior to prediction models or more generally, clients' behavior can evolve over time. Moreover, in practice, deploying a new model is a difficult procedure (for administrative and technical reasons).
  • Therefore, the models should be rather stable but adaptive to new behaviors.

  • And finally, these models should be accurate and efficient.
  • Scientific Objectives and Research Project :

    The goal of this thesis is to design efficient solutions meeting all the criteria described above.

    In order to be interpretable, rule-based or logic-based machine learning models will be the main focus. A large part of the research work will be devoted to analyse and compare the different models (decision trees, decisions sets, Boolean decision diagrams, etc.) in light of :

  • The properties usually sought-after in machine learning models (accuracy, efficiency, conciseness, etc.)
  • Their interpretability, in terms of the complexity of computing minimal explanations for a particular prediction, and on the empirical conciseness and interpretability of these explanations.
  • Their capabilities to handle imbalanced datasets and / or being somehow stable in the event of changes in the dataset due to adaptive behavior.
  • Then, the research will focus on the design of efficient methods to learn, explain and adapt the chosen model(s). The approaches can be either algorithmic or based on optimisation paradigms (Boolean Satisfiability, Constraint Programming, Integer Linear Programming, etc.

    Finally (and possibly) new machine learning models better adapted than existing ones may be proposed.

    Signaler cette offre d'emploi

    Thank you for reporting this job!

    Your feedback will help us improve the quality of our services.

    Mon email
    En cliquant sur « Continuer », je consens au traitement de mes données et à recevoir des alertes email, tel que détaillé dans la Politique de confidentialité de neuvoo. Je peux retirer mon consentement ou me désinscrire à tout moment.
    Formulaire de candidature