At a glance

Location: Paris, France
Work type: Onsite

What they are looking for

PythonPandasScikit-learnPysparkTime-series

Location: Paris, 75, FR

Internship - Modeling Consumer Spending Patterns

Paris, 75, FR

#job-location.job-location-inline {

display: inline;

}

ABOUT CFM

Founded in 1991, we are a global quantitative and systematic asset management firm applying a scientific approach to finance to develop alternative investment strategies that create value for our clients.

We value innovation, dedication, collaboration, and the ability to make an impact. Together, we create a stimulating environment for talented and passionate experts in research, technology, and business to explore new ideas and challenge existing assumptions.

Your Role

The Data-Insights-Alternative team works across a wide variety of structured and unstructured datasets, assessing their predictive power and preparing them for modeling. As data scientists, we work closely with the Research team to extract valuable insights from alternative data.

Consumer spending reflects evolving habits, preferences and financial constraints. The central project of your internship is to use alternative data to build interpretable consumer cohorts that remain stable over time. You will explore and compare different approaches to identify meaningful consumer profiles, including clustering, embedding methods and techniques inspired by recommender systems, with opportunities to experiment with agentic AI tools. You may also explore how these profiles can support predictive applications.

Documentation is a significant part of the job: you will read, synthesize and write a lot, so a good command of the scientific and technical literature is essential.

Key Responsibilities

Explore and understand large consumer spending datasets.

Aggregate and join heterogeneous data sources, and process huge datasets efficiently.

Review the academic and industry literature on consumer cohorts, embeddings and recommender systems, and identify the most relevant approaches.

Build and compare approaches to identify consumer cohorts: clustering, embeddings, recommender-system-inspired techniques.

Assess the interpretability and the stability over time of the cohorts obtained.

Experiment with agentic AI tools to support the analysis.

Explore how these profiles can support predictive applications.

Write clear documentation and reports on your methodology, results and limitations, and present them to the Alternative Data team (and, occasionally, to some researchers).

Your Skills

You are pursuing a Master's or engineering school degree (Bac+4/5) in data science, statistics, applied mathematics, computer science or a related field.

You are proficient in Python, Pandas and Scikit-learn. PySpark is a plus.

You have experience with time-series manipulation.

You are able to aggregate and join heterogeneous data sources and to manipulate huge datasets.

You are comfortable reading scientific papers and technical literature, and writing clear, well-structured documentation.

You are proactive, with a drive to experiment, test new approaches and propose original ideas.

You can communicate results and limitations clearly and concisely.

You are available for a six-month internship.

You are comfortable in both French and English.

EQUAL OPPORTUNITIES STATEMENT

We are continuously striving to be an equal opportunity employer and we prohibit any discrimination based on sex, disability, origin, sexual orientation, gender identity, age, race, or religion. We believe that our diversity, breadth of experience, and multiple points of view are among the leading factors in our success.

CFM is a signatory of the Women Empowerment Principles.