This analysis is based on the placement data of a B-school. I attempted to find answers the following questions:
-
How is salary correlated with given variables?
-
How are the variables related with the amount of salaries offered during placement?
-
Can the salaries be predicted based on the related variables?
-
How can this student cohort be categorized based on their distinct standing on different variables in the dataset?
My approach was simple. I used multiple linear regression model to understand the relationship betweeen salaries and other variables like gender, school and college level scores, work experience, scores on entrance exam for the job among others.
For the last question, I used clustering method - Gower's distance as it allows to measure distance for both categorical and continuous variables in one go.
Please read the analysis to find out more.