This project helps you understand how salaries vary across roles, locations, experience levels, and skills. The goal is to build a small dataset from job listings, clean salary information, analyse patterns, and create visuals that explain what drives pay. By the end, you will have a portfolio-ready project with clear insights and charts.
Project Goal
Analyse salary ranges for analytics roles (Data Analyst, Business Analyst, Reporting Analyst) and answer questions like:
- Which role titles pay more on average?
- How does salary change with experience?
- Which locations have higher pay?
- Which skills appear more often in higher-paying jobs?
Step 1: Collect job listing data
Collect 30 to 80 job listings that include salary information. Save these fields in a CSV:
- job_id
- title
- company
- location
- experience_min
- experience_max
- salary_min
- salary_max
- salary_currency
- salary_period (monthly or yearly)
- date_posted (optional)
- description_text
If salaries are given as text like “8–12 LPA” or “₹60k–₹90k per month”, keep the raw salary text too. You will parse it in Python.
Step 2: Clean and standardise salary
In Python:
- standardise salary to one unit (example: annual salary)
- convert monthly to yearly when needed
- convert ranges into a single value for analysis (example: midpoint of min and max)
- handle missing salary values by removing them from salary calculations
Also clean experience ranges and create a single experience value (midpoint).
Step 3: Extract skills from job descriptions
Create a skill dictionary and extract binary flags like:
- has_python, has_sql, has_excel, has_powerbi, has_tableau, has_statistics, has_cloud
This helps you compare pay patterns by skill requirements.
Step 4: Exploratory analysis (EDA)
Perform analysis such as:
- salary distribution (histogram + box plot)
- average salary by role title group
- average salary by location
- salary vs experience (scatter plot)
- top skills mentioned in high-salary jobs
Create salary buckets (low, mid, high) and compute which skills appear most in each bucket.
Step 5: Visualise insights
Create charts such as:
- bar chart: average salary by role
- bar chart: top locations by salary
- scatter plot: experience vs salary
- box plot: salary distribution by role
- heatmap: skill co-occurrence in high-paying jobs (optional)
Step 6: Write findings and recommendations
Write a short project summary:
- top paying roles and locations
- experience impact on salary
- skills most linked with higher salary buckets
- suggested learning priorities for job seekers
Deliverables
- cleaned_dataset.csv
- analysis_notebook.ipynb
- 4–6 saved charts
- README explaining data source, cleaning rules, assumptions, and key insights
This project is strong for a portfolio because it shows data cleaning, text feature creation, salary normalisation, and business-style insights.
