Stage - Quantitative Researcher H/F - Crédit Agricole Assurances

  • Stage
  • Paris 75
  • Télétravail
  • Finance
Stage - Quantitative Researcher H/F Crédit Agricole Assurances · Paris - 75 · Stage

Les missions du poste

Grâce à notre modèle de bancassurance, à notre expertise et à l'engagement de nos 7100 collaborateurs dans 10 pays, nous sommes le premier assureur en France et le premier bancassureur européen. Crédit Agricole Assurances répond aux besoins en protection et en épargne des particuliers, des agriculteurs, des professionnels et des entreprises. En France, notre gamme complète de produits et de services est distribuée par les Caisses régionales de Crédit Agricole et par LCL.

En agissant chaque jour dans l'intérêt de la société, nous sommes un groupe engagé en faveur des diversités et de l'inclusion et plaçons l'humain au coeur de toutes nos transformations. Tous nos postes sont ouverts aux personnes en situation de handicap.

Chez Crédit Agricole Assurances, la Direction des Investissements du Groupe propose des stratégies d'investissement à nos différentes filiales. Elle assure leur exécution et leur suivi dans le souci d'agir en faveur de la société et de nos clients.

Joint project between the Quantitative Research team at CAA and the CERMICS / Ecole des Ponts. The objective is to evaluate an existing implementation of a Decision-Focused Learning framework applied to portfolio optimization in a RL setting, and move from continuous to combinatorial decisions.

MISSIONS :

The objective of this internship is to implement and evaluate a Decision-Focused Learning (DFL) framework aiming to tackle the flaws of the traditional estimate, then optimize method. Instead, DFL core idea is to create a single, end-to-end system that learns to make the best possible investment decisions directly from data.
- As of today, a DFL framework applied to portfolio optimization is implemented under a continuous setting, and tested under a structured imitation learning approach to ensure the learning process occurs smoothly and correctly. The first challenge of this internship will be to move the existing framework towards a reinforcement learning setting to validate the agent capacity to take optimal decisions under different market regimes.
- Besides, portfolio optimization often involves making discrete (combinatorial) choices - and mathematical methods typically used to train neural networks work best with smooth, continuous problems, not discrete, combinatorial ones. The second (yet, key) challenge will be to bridge such gap, and identify the most suitable algorithm from the existing literature for training a network that includes a combinatorial optimization layer, specifically tailored to the unique uncertainties inherent in portfolio optimization.

Your internship mentor will support your integration and skill development.

BENEFITS

Professional opportunities within our Insurance units and the Crédit Agricole group, a remote work agreement, a 600 to 700 euro allowance to encourage sustainable mobility, and much more to discover!

RECRUITMENT PROCESS

1. An in-person or remote interview with the manager or internship mentor.
2. A phone call with an HR representative to arrange hiring details (internship start date, explanation of the hiring process, agreement, stipend).

This year, more than 100 interns have been welcomed into our teams. It's a concrete way to support young people in entering the job market, in line with the commitments set out in the Crédit Agricole Group's Youth Plan.

Environmental protection and social responsibility principles are integrated at the heart of our activities. All of our offers are open to people with disabilities.

Le profil recherché

Critères de candidature

:

Cadre / Non Cadre : Non cadre

Niveau d'étude minimum : Bac +5 / M2 et plus

Formation / Spécialisation :
Master en recherche opérationelle (RO), mathématiques de modélisation ou vision apprentissageA first professional experience is not required for the role.
Curiosity, creativity and proactivity are essential

Niveau d'expérience minimum : 0 - 2 ans

Soft skills :
Compétences techniques :
Statistics and probabilities
Machine learning
Deep learning
Data science

Compétences comportementales :
Avoir le sens du résultat
Etablir des priorités
Gérer efficacement les délais et les imprévus
Proposer des initiatives ou des solutions
Travailler en mode projet
Capacité à écrire du code clair





Outils informatiques :
Python

Ces offres pourraient aussi vous correspondre.

Parcourir plus d'offres d'emploi