Data Analyst Course With Power BI & SQL

Light
Dark

AI Data Analytics Mastery

By Shailja In Grow Data Skills

Self Paced
English
Completion Certificate

Demo Class Video

1 Year

Validity (From the date of Enrollment)

70 Hours

Duration

14

Sessions

2

Projects

INR 8000

Buy Now

This course includes

Content Duration70 Hours
Total Sessions14
Total Industry Projects2
Pre-reads content for SQL, Power BI & Python
Quality Assignments & quizzes after each module
Interview preparation guide
Dedicated placement assistance
Resume & Linkedin profile making
Offline doubt support on private discord group
Certificate of completion

Tech stack you'll learn

Course Content

✅ Class - 1 | Data Analytics Foundations + AI Shift

What is Data Analytics
Real-world definition: from raw data to business decisions
The analytics value chain: Data → Information → Insight → Action
Who uses analytics and why it matters in 2026 (Finance, Retail, Healthcare, SaaS)
Difference between a Data Analyst, Data Scientist, and Data Engineer
Types of Analytics
Descriptive Analytics – What happened? (Reports, dashboards, KPIs)
Diagnostic Analytics – Why did it happen? (Drill-downs, root cause)
Predictive Analytics – What will happen? (Forecasting, ML basics)
Prescriptive Analytics – What should we do? (Recommendations, AI agents)
Real-world example for each type using business scenarios
How AI is Changing Analytics
Before AI vs After AI: The analyst's workflow in 2026
AI as a co-pilot: faster cleaning, instant insights, automated reports
Democratization of analytics: non-technical users doing analytics with AI
What skills still matter (critical thinking, domain knowledge, storytelling)
Risks of AI in analytics: hallucinations, bias, over-reliance
Tools Landscape 2026
Excel / Google Sheets: Still relevant for quick analysis and business users
SQL: The universal language of data – every analyst must know it
Power BI / Tableau: Visualization and dashboarding
Python: For automation, advanced analytics, and AI integration
AI-native tools: ChatGPT, Claude, Gemini, Copilot, Julius AI, Notebook LM
Live demo: The same task done in Excel, SQL, Python, and AI
Hands-on Activity
Explore a real dataset (e.g., sales or HR data) in Excel
Identify which type of analytics applies to 5 business questions
Discussion: Which tools does your dream company use?

✅ Class - 2 | AI for Data Analytics

Prompt Engineering for Analysts
What is prompt engineering and why it is a core skill in 2026
Anatomy of a good prompt: Role + Context + Task + Format + Constraints
Zero-shot, few-shot, and chain-of-thought prompting
Common mistakes in prompting and how to fix them
Building a personal prompt library for analytics tasks
AI for Data Cleaning
Using ChatGPT / Claude to identify data quality issues
Prompting AI to write cleaning steps and suggest transformations
Detecting outliers, duplicates, and inconsistencies with AI assistance
Hands-on: Clean a messy CSV using AI-generated instructions
AI for SQL Generation
Describing a business question in plain English → getting SQL output
Validating and understanding AI-generated SQL before running it
Iterative prompting: refining SQL through conversation
Tools: ChatGPT, Claude, GitHub Copilot etc.
AI for Insight Extraction
Uploading data to AI tools and asking for key trends
Using AI to write executive summaries from data
Generating charts and visualizations through prompts (Julius AI, ChatGPT Advanced Data Analysis)
Asking the right business questions to get useful AI insights
Case Study
Analyze a 500-row e-commerce dataset manually
Repeat the same analysis using AI tools
Compare: speed, accuracy, depth of insights
Debrief: Where does the analyst still add value?

📌 Fundamentals of Excel (Pre-read as recorded)

✅ Class - 3 | Excel for Analytics

Essential Formulas
Lookup functions: VLOOKUP, HLOOKUP, INDEX-MATCH, XLOOKUP (2026 standard)
Logical functions: IF, IFS, AND, OR, nested logic
Text functions: LEFT, RIGHT, MID, TRIM, CONCATENATE, TEXTJOIN
Date and time functions: TODAY, DATEDIF, EOMONTH, WEEKDAY
Statistical functions: SUMIF, COUNTIF, AVERAGEIF, SUMPRODUCT
Dynamic arrays: FILTER, SORT, UNIQUE, SEQUENCE
Pivot Tables & Charts
Building pivot tables from scratch: rows, columns, values, filters
Grouping dates by month, quarter, year in pivots
Calculated fields and items inside pivot tables
Pivot charts: choosing the right chart for the right data
Slicers and timelines for interactive dashboards
Data Cleaning in Excel
Identifying and removing duplicates
Handling blank cells, errors (#N/A, #DIV/0!), and inconsistent formats
Text-to-Columns and Flash Fill for data splitting
Standardizing categories with Find & Replace and data validation
Using conditional formatting to highlight data issues
Intro to Power Query
What is Power Query and why it replaces manual cleaning steps
Connecting to CSV, Excel, and web sources
Applied steps panel: transformations are recorded and replayable
Common transformations: unpivot, merge, append, split column
Refreshing data: the power of automated pipelines
Case Study
Receive a messy HR or sales dataset with 20+ data quality issues
Clean, transform, and build a pivot summary in Excel
Present findings as a one-page summary table

✅ Class - 4 | AI + Excel Automation

AI Formula Generation
Prompting AI to write complex Excel formulas from plain English
Explaining formulas back using AI (great for debugging)
Using AI to convert old VLOOKUP logic to modern XLOOKUP/FILTER
Building conditional logic and nested formulas with AI guidance
Error-fixing: pasting broken formulas into AI and asking for fixes
Microsoft Copilot in Excel
Overview of Excel Copilot features available in 2026
Using Copilot to generate pivot tables and charts from natural language
Asking Copilot to highlight trends, anomalies, and insights
Copilot for formula suggestions and data transformations
Limitations and when NOT to trust Copilot output
Automating Reports
Building a dynamic monthly report template with named ranges
Automating data refresh with Power Query + scheduled connections
Creating reusable dashboards with dropdowns and slicers
Introduction to Excel macros concept (recording, not deep VBA)
Using AI to understand and modify recorded macros
Automation Thinking
The mindset shift: from doing once to building for repeat use
Mapping manual tasks that can be automated (the automation audit)
Version control: naming conventions for Excel files in teams
Case Study
Build a complete automated monthly sales report in Excel
Use AI prompts to generate all formulas and chart logic
Use Excel Copilot to summarize the report findings
Final output: a ready-to-share professional report

📌 Fundamentals of SQL (Pre-read as recorded)

✅ Class - 5 | SQL for Analytics

SQL Foundations
What is a relational database? Tables, rows, columns, keys
JOINs
Understanding relationships: one-to-many, many-to-many
Common mistakes with JOINs and how to debug them
Subqueries & CTEs
When to use subqueries vs CTEs vs temp tables
Nested CTEs for multi-step analysis
Window Functions
What window functions do and why they are essential for analytics
Real Business Queries
Find top 10 customers by revenue in the last 90 days
Calculate month-over-month sales growth
Identify churned users (no activity in 30 days)
Cohort retention: users who returned after first purchase
Practice set: 10 business questions → write SQL

✅ Class - 6 | AI + SQL

AI SQL Generation
Translating business questions to SQL using ChatGPT and Claude
Providing schema context to AI: how to share table structures effectively
The review-before-run rule: always validate AI SQL
Iterative SQL refinement through follow-up prompts
Using AI to add comments and documentation to SQL queries
Query Optimization
Understanding why queries are slow (full scans, missing indexes)
Using EXPLAIN / QUERY PLAN to analyze query execution
Prompting AI to rewrite slow queries for better performance
Partitioning concepts for large datasets
Debugging with AI
Pasting SQL errors into AI and asking for diagnosis
Common SQL errors: ambiguous columns, NULL handling, type mismatches
Using AI to explain what a complex legacy query does
Case Study
Receive 5 complex business questions from a mock e-commerce database
Convert each to SQL using AI assistance (with schema provided)
Run, validate, and interpret results
Discussion: What did AI get right? What needed correction?

📌 Fundamentals of Power BI (Pre-read as recorded)

✅ Class - 7 | Power BI Basics

Power BI Ecosystem
The Power BI workflow: Get Data → Model → Visualize → Publish
Connecting to data sources: Excel, CSV, SQL Server, SharePoint, web
Power Query in Power BI: transformations and data shaping
Data Modeling
Star schema vs flat tables – why modeling matters for performance
Creating relationships between tables in the Model view
Cardinality: one-to-many, many-to-many – handling each correctly
Dimension tables vs fact tables in practical projects
Visualizations
Choosing the right visual: bar, line, scatter, map, card, table, matrix
Building slicers and filters for interactivity
Drill-through and drill-down for hierarchical data
Formatting best practices: colors, fonts, alignment, whitespace
Case Study
Import a multi-table retail dataset into Power BI
Build relationships and create a star schema model
Build a complete sales dashboard with 6+ visuals and slicers
Present the dashboard to the class with a 2-minute walkthrough

✅ Class - 8 | Dashboards + Storytelling + AI Analytics

DAX Fundamentals
What is DAX and why it is the engine of Power BI analytics
Calculated columns vs measures – understanding the difference
Basic measures: SUM, AVERAGE, COUNT, DISTINCTCOUNT
KPI Dashboard Design
Defining the right KPIs for a business (lagging vs leading indicators)
RAG status indicators (Red/Amber/Green) using conditional formatting in DAX
Sparklines and micro-charts for compact trend display
Bookmarks and buttons for multi-page navigation in Power BI
Power BI Copilot
Overview of Power BI Copilot features in 2026
Using Copilot to generate DAX measures from natural language
Asking Copilot to build visuals and suggest layout improvements
Q&A feature: letting stakeholders ask questions of the dashboard
AI Insights: anomaly detection and key drivers visual
Case Study
Build a full executive business dashboard with 8+ KPIs
Present the story behind the data in a 5-minute mock stakeholder pitch

📌 Fundamentals of Python (Pre-read as recorded)

✅ Class - 9 | Python for Analytics

Pandas for Data Analysis
Selecting and filtering data: loc[], iloc[], boolean masks
Handling missing values: isnull(), fillna(), dropna()
Data transformations: apply(), map(), lambda functions
Groupby and aggregation: groupby().agg() with multiple functions
Merging datasets: merge(), concat(), join() – the pandas equivalent of SQL JOINs
Sorting, ranking, and deduplication with drop_duplicates()
Exploratory Data Analysis (EDA)
The EDA workflow: understand → clean → explore → visualize
Detecting outliers using IQR method in code
Visualization in Python
Matplotlib: plot(), bar(), pie(), subplots
Seaborn for statistical plots: heatmap, pairplot, boxplot, violinplot
Hands-on Practice
Load and explore a real-world dataset (e.g., Netflix, Airbnb, or IPL data)
Perform full EDA: shape, nulls, distributions, correlations
Create 5 visualizations that tell a story about the dataset

✅ Class - 10 | AI + Python Analytics

AI-Assisted Python Coding
Using ChatGPT, Claude, and GitHub Copilot to write Pandas code
Describing what you want in English → getting working Python code
Reviewing, testing, and modifying AI-generated code
Debugging Python errors by pasting the traceback into AI
Cursor IDE: AI-native coding environment overview
AI Analytics Libraries
PandasAI: querying DataFrames with natural language
LangChain with Pandas for conversational data analysis
Intro to scikit-learn: training a simple predictive model in 10 lines
Using pre-trained models for quick predictions (Prophet for forecasting intro)
Case Study
Build an AI-generated analytics pipeline from scratch
Task: Load raw data → Clean → Analyze → Visualize → Export report
Entire pipeline written using AI assistance

✅ Class - 11 | AI Agents for Analytics

What are AI Agents?
AI agents vs AI assistants: the key difference (autonomy and multi-step tasks)
Anatomy of an AI agent: LLM + Tools + Memory + Planning
Real-world analytics agents in 2026: examples from companies using them
LangChain Basics
What is LangChain and why it matters for analytics agents
Chains vs Agents in LangChain
Business Insights Agent
Building an agent that answers business questions from a dataset
Connecting an LLM to a CSV or database using LangChain basics
Building a simple Q&A interface over your data in Python (demo)
No-Code AI Agent Tools
Make.com (Integromat): building data workflows visually
n8n: open-source automation with AI nodes
Zapier with AI: connecting apps and triggering AI actions
Power Automate + Copilot: Microsoft's agentic workflow tool
Choosing the right tool: code vs no-code tradeoffs

✅ Class - 12 | RetailPulse AI (Project - 1)

RetailPulse AI — Automated Business Intelligence Agent
Build an end-to-end AI agent that autonomously computes weekly KPIs
Detects performance anomalies across retail data
Delivers AI-written executive reports — eliminating 4 hours of manual analyst work every week

✅ Class - 13 | ChurnShield Analytics (Project - 2)

ChurnShield — Customer Intelligence & Churn Prediction Platform
Develop a 3-layer customer analytics system that segments 7,000+ telecom customers
Predicts churn with 84% accuracy using ML models
Generates AI-powered retention strategies — identifying high-risk customers before they leave

✅ Class - 14 | Career Guidance, Resume & Portfolio Creation

Career Roadmap for Data Analysts in 2026
Resume Building for Data Analyst Roles
Portfolio Creation – Showcasing Projects on GitHub / LinkedIn
Interview Preparation – SQL, Python, and Case Study rounds
Networking and Job Search Strategy

Course Schedule

Mode Of The Course:

Self Paced

Course Duration:

70 Hours

Total Sessions:

Total Projects:

Course Validity:

1 year

Programming Language Used:

Python

Prerequisite:

Passion And Willingness To Learn

⚠️ Important Notice :

The video may not work on Linux due to DRM restrictions. It is only accessible on Chrome when using Windows or macOS.

Workaround: To access the video on Linux, you can create a Windows virtual machine (VM) and watch the video through the VM. Alternatively, you can use our Android or iOS application to view the video on your mobile device.

Instructor

Shailja Mishra

Shailja Mishra is a Data and Applied Scientist at Microsoft , mentored over 1000+ Students around Data Analysis Domain.

AI Data Analytics Mastery (Self Paced)

INR 8000

Buy Now

AI Data Analytics Mastery

1 Year

70 Hours

14

2

Tech stack you'll learn

Course Content

Module 1 - Foundations + AI Mindset

Module 2 - Excel + Data Cleaning

Module 3 - SQL + Data Thinking

Module 4 - Visualization + Power BI

Module 5 - Python + AI Analytics

Module 6 - AI Agents + Industrial Projects

Module 7 - Career Guidance, Resume & Portfolio Creation

Course Schedule

Instructor

Shailja Mishra

AI Data Analytics Mastery (Self Paced)

Namaste 🙏