All projects

Adapting a company rating model

Adapting a rating model to technical constraints and exposing it through a web service.

Professional experienceCredit risk

An assignment from my professional background. No internal or confidential data is disclosed.

Abstract illustration of the main data flow — no internal or confidential data is shown.

Context

From November 2019 to June 2021, I contributed through Apside to adapting and updating a company rating model within Banque de France’s Artificial Intelligence team.

  • Company data used for rating
  • Data needed to run the model

Challenge

The model, used to assess credit risk, needed to be adapted to the target technical environment and exposed through a web service.

Objectives

  • Adapt the model to technical constraints.
  • Update the associated processing and prepare the data.
  • Make the model accessible through a web service.

Contribution

I contributed to adapting the model, updating its processing and exposing it through a web service. During this assignment, I also developed a prototype to predict property prices per square metre.

  • Adapting the model and maintaining its associated processing.
  • Preparing and analysing the data needed by the model.
  • Developing a web service to expose the model.

Work carried out

A contribution to adapting the rating model, maintained processing and a web service developed to expose the model.

Technologies

  • Python
  • Pandas
  • NumPy
  • Scikit-learn
  • Matplotlib
  • ONNX

A similar challenge?

Facing a similar challenge? Let’s talk.

Describe your data, processes and objectives to discuss an engagement suited to your needs.

Discuss your project