Skip to content

Latest commit

 

History

History
22 lines (15 loc) · 995 Bytes

README.md

File metadata and controls

22 lines (15 loc) · 995 Bytes

Model drift detection using explainability algorithms

Juan Carlos Ruiz Ruiz

Introduction

This is the final work from the Master in Software Engineering and Artificial Intelligence imparted by the University of Malaga.

This project is based on the idea of using explainability algorithms to detect model drifting in on-line prediction models. It explores the use case of the forecasting of tourists in the province of Malaga and we develop a methodology to test a model and detect if it is drifting.

Installation

Prerrequisites

  • Python 3.10 or higher
  • Jupyter Notebook

Local installation

There is no need to install any specific technology. The code may be found in the Jupyter Notebook regression_tourism_final.ipynb.

To use this code locally clone this repository and open the notebook desired:

git clone https://github.com/JCruiz15/explanable-model-drift