CASE STUDY · DATA ANALYSIS
Job Market Skills Intelligence Dashboard
A beginner project using 10,000 synthetic job postings. I wanted to see which skills come up most often and how that changes by role.
Problem & goal
When you look at job postings, it's hard to tell which skills come up most. I wanted to answer that with a simple, clear process. I kept the scope small on purpose.
Data
The dataset has about 10,000 synthetic job postings. It isn't real scraped data. Each posting has fields like job title, company, location, experience level, salary range, skills and posting date. Because the data is synthetic, any patterns come from how it was generated, not from the real job market.
What I did
- Loaded the raw data into Python with Pandas, checked it, dealt with missing values and made inconsistent text consistent
- Wrote SQL queries to count postings by skill, role and experience level
- Checked the SQL results in Excel with PivotTables and formulas
- Built a Power BI dashboard with cards, bar and column charts and slicers
Process
Output
Findings
The data is synthetic, so I'm not treating the skill counts as real job market findings. They mostly show how the dataset was made. What the project does show is the full process, from raw data to a dashboard.
Limitations
- The data is synthetic, so this isn't real market analysis
- No statistical testing. It only uses grouping and counts
- The dashboard isn't shown on this site yet
What I learned
A lot of the work is deciding what to show. It was easy to keep adding charts. It was harder to keep only the ones that answered the question.