ENSAE Paris - École d'ingénieurs pour l'économie, la data science, la finance et l'actuariat

Projet d'approfondissement en finance et assurance - S2

Enseignant

TANKOV Peter

Département : Finance

Objectif

Students of the M2 "Statistics, Finance and Actuarial Science" and students of the Actuarial Science and Finance & Risk Management tracks of ENSAE have the opportunity to participate in prospective work, in groups of 3 or 4 and under the guidance of a supervisor, professional of the financial industry or researcher in finance / insurance. The supervisor will meet with the students once or twice a month to coordinate and guide their work, in person or by videoconference. He/she will also provide the students with the data necessary to carry out the project.

These in-depth projects focus on a well-identified subject of quantitative finance, risk management, or insurance, and present a
genuine interest for the company/laboratory. For example, it can be an exploratory research around a new model, the analysis of a
specific database or the study and development of a new portfolio management strategy. Projects will include
typically a bibliographic research step, a data analysis step and a computer implementation step. Although the results of the project can be interesting and useful for the company, it is by no means a consultancy assignment.
The objective is to be forward-looking, to test innovative ideas.

The publication of an article as the result of such work could be considered in certain cases.

The studens must submit an interim report at the end of January, a final report in May and pass an oral defense. This is a full course, which will validate 3 ECTS in the first semester and 3 ECTS in the second semester.

List of projects proposed in 2021-2022 (detailed descriptions well be published in October):

Finance:

1. Crédit Agricole CIB: Corrélations hybrides

2. BNP Paribas: Generative adversarial network : simulation de prix d’actifs financiers et strate?gie de couverture

3. Scalnyx (fournisseur de solutions AI pour les gestionnaires de fonds) Tactical Asset Allocation using Bayesian Machine-LearningTactical Asset Allocation using Bayesian Machine-Learning

4. Varenne Capital Partners (Hedge Fund): Build a toy market simulator with to design macro reward signals to be used in a reinforcement learning framework for trading

5. Alpha Foundry (Hedge fund): Marchés Crypto - A la Redécouverte de la Convexité 

6. Electricité de France: Prévision de carnets d’ordre du marché day-ahead de l’électricité 

7. Market Cipher (Hedge fund): S&P et Contrats futures sur le VIX 

Actuarial Science:

8. Milliman : Estimation de la mortalité due aux risques climatiques

9. Deloitte Conseil : Modélisation du risque physique climatique – Intégration du changement climatique dans la projection de la sinistralité assurantielle

10. Generali : Modélisation de la valeur Client en assurance vie dans un contexte Big Data

11. Pacifica : Les mécanismes d’assurance collaborative dans le secteur agricole

12. LinkPact: Prediction moyen-terme de l'évolution de la pandemie COVID-19

Plan

The indicative timetable for the projects is as follows:
- Beginning of October: dissemination of subjects to students, constitution of groups
- End of January: submission of the mid-term report
- Beginning of May: submission of the final report
- Before the end of May: defense

This course aims in particular to give students the following skills:
- Bibliographic research
- Analysis of financial data
- Formulation and implementation of a mathematical model from a business problem
- Methodology and requirements of industrial / university research