UNIT-II: Data Analytics – Extended
Notes with Diagrams and Tables
1. Introduction to Data Analytics
Data Analytics refers to examining datasets to uncover hidden patterns, correlations,
trends, and insights. It empowers organizations to make data-driven decisions. Analytics is
a backbone of strategic planning and business intelligence.
Example: Amazon uses data analytics to recommend products based on customer behavior,
past purchases, and browsing history.
Types of Analytics:
1. Descriptive – What happened?
2. Diagnostic – Why did it happen?
3. Predictive – What is likely to happen?
4. Prescriptive – What action should be taken?
Use Case: In healthcare, predictive analytics can forecast disease outbreaks by analyzing
past patient records and environmental factors.
Type Purpose Example
Descriptive Summarizes past data Sales report
Diagnostic Identifies reasons for events Customer churn analysis
Predictive Forecasts future outcomes Sales prediction
Prescriptive Suggests next actions Marketing strategy
optimization
2. Tools and Environment for Data Analytics
Analytics tools process data, build models, and visualize results. The environment refers to
where analytics tasks are performed — local machines, enterprise servers, or cloud.
Python and R are programming languages widely used for statistical modeling and data
analysis.
Tableau and Power BI are visualization tools for creating interactive dashboards.
SQL is essential for querying structured databases.
Cloud environments such as AWS and Azure provide scalable resources for handling large-
scale analytics.
Tool Category Key Use
Python Programming Data preprocessing,
modeling
R Statistical Advanced statistical
analysis
SQL Query Language Database management
Tableau Visualization Creating dashboards
AWS Cloud Hosting and processing data
3. Application of Modeling in Business
Business modeling uses data to simulate different scenarios, forecast results, and optimize
operations. Models convert data into actionable business insights.
Use Case: Netflix models user preferences to provide personalized movie recommendations.
Regression models predict values like sales or revenue. Classification models categorize
emails as spam or not spam. Clustering groups similar customers for targeted marketing.
Advanced modeling helps in inventory management, fraud detection, and operational
efficiency.
4. Database and Types of Data and Variables
A database is an organized collection of data. Relational databases like MySQL use
structured tables. NoSQL databases like MongoDB handle unstructured data.
Data types:
- Structured: Organized (e.g., Excel files)
- Semi-structured: Tags but not tables (e.g., JSON)
- Unstructured: No format (e.g., videos)
Variables:
- Numerical: Age, Salary
- Categorical: Gender, City
- Ordinal: Low, Medium, High
Data Type Format Example
Structured Rows/Columns Database Tables
Semi-structured Tags XML, JSON
Unstructured Freeform Images, Text
5. Data Modeling Techniques
Data modeling provides a visual representation of data elements and their relationships. It’s
crucial in designing databases and ensuring efficient data flow.
Conceptual models focus on business entities and relationships. Logical models define data
structure. Physical models describe how data is stored.
Entity-Relationship (ER) diagrams, Normalization, and Dimensional Modeling (Star
Schema) are common techniques.
6. Missing Value Imputations
Missing values reduce model accuracy and can introduce bias. Imputation is the process of
replacing missing data with substituted values.
Techniques include:
- Mean/Median: Replace with average/central value
- KNN: Uses nearest data points to fill gaps
- Regression: Predicts based on relationships with other variables
Handling missing data ensures dataset completeness and model reliability.
Technique Approach Best Use Case
Mean Fill with average Numerical values
Median Fill with central value Skewed data
KNN Use nearest neighbors Small datasets
Regression Predict with model Correlated variables
7. Need for Business Modeling
Business modeling is essential for understanding, analyzing, and optimizing business
processes. It supports digital transformation and operational planning.
Models like SWOT help identify internal strengths and external threats. BPM (Business
Process Modeling) outlines workflow structure.
Use Case: Uber uses business modeling to match rider demand with driver supply in real-
time.