The dataset folder contains the following files:

• train.csv: 90 x 2
• test.csv: 60 x 1
• trainResumes: 90 resumes that you must use for training model
• testResumes: 60 resumes that you must use for testing model
• Job description.pdf: PDF file that represents the job description of a Machine Learning engineer

score = 100*max(0, 1 - metrics.mean_squared_log_error(actual, predicted))

LightBGM algorithm with counvectorized data has the highest score.