Glassdoor-Salary-Prediction: Overview

• Collected, Cleaned and Analysed data from glassdoor.com

• Performed Feature Engineering on various textual, categorical and numerical features in order to extract the significant areas to contribute to the model

• Performed predictive modelling on the data using a variety of ML algorithms

• Performed Hyperparameter Tuning to improve model performance

• Evaluated the implemented machine learning models to get a MAE of 12.69

• Implemented a Flask endpoint

Code and References

• Python Version: 3.7

• Packages: numpy, pandas, matplotlib, seaborn, selenium, pickle

• Selenium Scraper: https://github.com/arapfaik/scraping-glassdoor-selenium

• Code Reference: https://github.com/PlayingNumbers/ds_salary_proj.git

• Productionization: https://towardsdatascience.com/productionize-a-machine-learning-model-with-flask-and-heroku-8201260503d2