All projects

Productionising a risk analysis model

Bringing a risk analysis model into production and making its outputs usable.

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

Within an Artificial Intelligence team, I contributed to the productionisation and development of a company rating model for credit risk assessment.

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

Problem and challenge

The model needed to be adapted to the technical environment and exposed for use by other components.

Objectives

  • Adapt the model to technical constraints.
  • Maintain its processing and prepare the data.
  • Expose the model through a web service.

Contribution

I contributed to model adaptation and maintenance, data preparation and analysis, and the development of its web service.

  • Adapting the model and maintaining its associated processing.
  • Preparing and analysing data with Python, Pandas and NumPy.
  • Developing a web service to expose the model.

Outcome

A model adapted to the technical environment, maintained processing and a web service exposing the model.

Technologies

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

A similar challenge?

Facing a similar challenge? Let’s talk.

Let’s discuss your data, processes and expected outcome to define an engagement that fits your context.

Discuss your project