Salary_prediction

Aims to build and test classification models to predict salaries from the text contained in the job description.

This project will create classification models to predict high (75th percentile and above) or low (below 75th percentile) salary from the text contained in the job descriptions, with the usage of Naïve Bayes classifier.

Steps:

1. Build a classification model with text (full job description) as the predictor.
2. Calculate the model accuracy.
3. Show the top 10 words (excluding stopwords) that are most indicative of (i) high salary, and (ii) low salary.

See Salary Prediction Jupyter Notebook for detailed analysis

The data for this project can be found at http://www.kaggle.com/c/job-salary-prediction (“Train_rev1.csv”).