The short answer
To become a data analyst, learn Excel first, then SQL, then basic statistics, then one visualisation tool such as Power BI or Tableau. Add Python once those are solid. Build three projects on real datasets that each end with a clear insight, publish them, and apply for analyst, MIS and reporting roles. Most students can cover this in four to six months of steady part-time work.
What a data analyst does
A data analyst turns raw data into answers a business can act on: which products sell, where customers drop off, which campaign worked. Entry-level titles include Data Analyst, MIS Executive, Business Analyst, Reporting Analyst and Operations Analyst.
A typical day involves pulling data with SQL, cleaning it, building or updating a report or dashboard, and explaining what the numbers mean to someone who is not technical. The explaining is as important as the analysis.
The roadmap, phase by phase
Phase 1: Excel or Google Sheets
Weeks 1 to 4
Spreadsheets are still the most used analysis tool in Indian companies, and the fastest way to start thinking in data.
- Formulas: IF, SUMIFS, COUNTIFS, XLOOKUP or VLOOKUP, text and date functions
- Sorting, filtering, removing duplicates, data validation
- Pivot tables and pivot charts
- Clean, readable charts
Output: One Excel project: a cleaned dataset, a pivot-based summary and a one-page dashboard.
Phase 2: SQL
Weeks 5 to 10
SQL is the most requested skill in analyst job descriptions. Practise on a real database, not only in a browser quiz.
- SELECT, WHERE, ORDER BY, GROUP BY, HAVING
- Joins: inner, left, self
- Subqueries and common table expressions
- Window functions: ROW_NUMBER, RANK, running totals
- Date and string functions
Output: 50 to 80 SQL problems solved and one project answering 10 business questions on a multi-table dataset.
Phase 3: Statistics you will actually use
Weeks 9 to 12
You need working statistics, not a full degree in it.
- Mean, median, mode, variance, standard deviation
- Distributions, percentiles and outliers
- Correlation versus causation
- Sampling, hypothesis testing and A/B test basics
Output: A short write-up interpreting one dataset: what is typical, what is unusual and what might explain it.
Phase 4: Data visualisation
Weeks 12 to 16
Pick Power BI or Tableau. Power BI appears more often in Indian job posts; Tableau Public is easier for sharing work. Learn one properly.
- Connecting and modelling data
- Choosing the right chart for the question
- Filters, slicers and drill-downs
- Basic DAX (Power BI) or calculated fields (Tableau)
- Designing a dashboard a manager can read in one minute
Output: One published dashboard with a paragraph summarising the three main findings.
Phase 5: Python for analysis
Weeks 16 to 22, optional for a first job
Python lets you handle bigger data and automate repetitive work. Learn it after SQL, not instead of it.
- Python basics
- pandas for cleaning and analysis
- matplotlib or seaborn for charts
- Jupyter notebooks
- Using AI assistants to draft and check code
Output: One notebook that cleans a messy dataset and answers five questions about it.
Phase 6: Portfolio and business thinking
Weeks 20 to 26
Tie the tools together and learn to present your work.
- Three projects: one Excel, one SQL, one dashboard
- A README or case study for each: question, data, method, findings, recommendation
- Common metrics: revenue, growth, retention, conversion, churn
- Practising explaining a project in two minutes
Output: A portfolio page or GitHub profile linking all three projects.
Skills checklist
| Skill | Level needed for a first job | Priority |
|---|---|---|
| Excel / Google Sheets | Pivot tables, lookups, charts, clean formatting | Essential |
| SQL | Joins, aggregations, subqueries, window functions | Essential |
| Power BI or Tableau | One complete interactive dashboard | Essential |
| Statistics | Descriptive statistics, basic hypothesis testing | Important |
| Communication | Explaining a finding in plain language | Important |
| Python | pandas basics | Helpful |
| AI tools | Drafting queries, checking logic, summarising | Helpful |
Project ideas with real data
- Sales analysis for a retail dataset: best products, seasonality, regional performance.
- IPL or cricket statistics: what actually predicts a win.
- Zomato or Swiggy restaurant data: pricing, ratings and cuisine trends by city.
- Government open data from data.gov.in: education, health or agriculture trends for your state.
- Your own data: a month of expenses, study hours or screen time, analysed honestly.
How to get your first interview
- Rewrite your resume around your projects and the exact skills in data analyst job descriptions.
- Publish your work where recruiters can see it, and write one LinkedIn post per project.
- Apply to internships first. They have a lower bar and often convert into full-time offers.
- Message alumni and people one or two years ahead of you in this role. Ask one specific question before you ask for a referral.
- Track every application in a sheet, and after each interview write down the questions you could not answer.
Frequently asked questions
Can I become a data analyst without a technical degree?
Yes. Analyst roles are open to commerce, management, economics, science and arts graduates. Employers check whether you can use Excel and SQL and explain your findings, which you can prove with projects.
Do I need to learn Python to get a data analyst job?
Not for many entry-level roles, where Excel, SQL and a dashboard tool are enough. Python becomes more valuable as you grow, so learn it after the basics are strong.
Should I learn Power BI or Tableau?
Either works, and the concepts transfer. Power BI is common in companies that use Microsoft tools and appears frequently in Indian job listings. Tableau Public makes it simple to share a portfolio. Check job posts for the roles you want and pick the one that appears more.
What is the difference between a data analyst and a data scientist?
A data analyst explains what happened and why, using SQL, spreadsheets and dashboards. A data scientist also builds predictive models using machine learning and usually needs stronger programming and statistics. Many people start as analysts and move across later.
