Linkedin salary prediction

End-to-end project to predict salary for job offers on Linkedin


This project presents an end-to-end machine learning solution to problem of predicting salary from job offers posted on linkedin.
This projects consists of the following steps:

  • Data collection: Web-scraping script for the linkedin website
  • Data preprocessing and feature engineering
  • Model selection, training, and fine-tuning: Training more than 100 models using bayesian optimization to fine-tune hyperparameters.
  • Model evaluation: Mlflow for comparing model performances
  • Model deployment: deployment on AWS using fastapi
  • Model monitoring: data quality, data drift and model performances.
Linkedin salary model


The libraries and tools used for this project were: python, AWS lambda, scikit-learn, pandas and mlflow.

© Copyright Max Lutz 2023 - All Rights Reserved