Société Générale

Join the Societe Generale Team!


Societe Generale opened its first office in the United States in 1938 and in Canada in 1974. Today, it is one of the largest foreign banking organizations in North America, with approximately 2,500 professionals working in eight US cities, in three cities in Canada and in Mexico City.

The following Societe Generale divisions operate in the United States and Canada to provide investor, corporate and government clients with financial solutions.

  • Corporate & Investment Banking : Securities, derivatives brokerage, investment banking, asset management, advisory services, execution and prime brokerage through the Societe Generale Branch, SG Americas Securities and Lyxor.
  • Specialized Financial Services : Equipment finance services through SG Equipment Finance USA Corp.

Industry : Corporate & Investment Banking (CIB) and Financial Services
Founded : 1974


Are you interested in solving concrete industrial problems while developing a unique work experience? Fill in the participation form below. We will review your eligibility and provide you with the registration link later.


Categorical variable selection in risk modelling

In financial institutions, categorical features appear quite often in credit datasets and in compliance models, for example, features related to clients’ risk profile.

Traditional feature selection methods (e.g. statistical significance, recursive feature elimination, LASSO) do not work well with categorical features since these methods would retain certain levels and remove other levels of the same feature. The Group Lasso approach has shown to be more stable in terms of variable selection but displays shortcoming in terms of predictability. Instead, for a given feature, would it be more appropriate to devise a method that aggregates neighbouring levels in bins in order to get a feature representation space that would better scale with the output?

Because of the numerous ways to represent categorical variables and to select which variables are of importance we ask what are the most appropriate methods for improving categorical feature selection?

  • Have a model framework, based on the literature, comparing the pros and cons of several different variable selection method.
  • Compare various model performances based on their dataset.

The dataset will be used is anonymized banking and credit data.


Alejandro Murua
Full Professor  – Department of Mathematics and Statistics, University of Montreal.

Adrian Gonzalez Sanchez
Lecturer, HEC Montréal and Concordia University.

Helena Liu
Model Validation Manager VP, Société Générale.

Jiaxin Yang
Quantitative Advisor, Société Générale.

Zouheir Malki
Partnership Advisor, IVADO.

  • Name:
  •  Background: