Deep Dive into Tech Pay: Revealing India’s Software Professionals’ Salaries through SHAP Values

Newest available salaries for India’s software professionals: SHAP values for job title, location, and company name

Photo by rupixen.com on Unsplash

In this article, I use the Software Industry Salary Dataset taken from the https://www.glassdoor.co.in website which contains about 22,700 reported yearly salaries for India’s software professionals. The dataset is also publicly available on Kaggle. Full details of the analysis can be found in this public Kaggle notebook.

Step 1 — data preprocessing

Here, data preprocessing consists of the following steps:

• converting the label (yearly salaries) to Lakh (= 100,000) INR;
• excluding 1% of the highest and 1% of the smallest salaries as potential outliers;
• renaming selected job titles;
• encoding rare categorical variables (in the company name, job title, and location columns) with no more than 30 different categories in each column and at least 20 data samples in each category;
• finally, dropping unused columns.