Notes on Data Analytics

Introduction to Data Analytics

What is Data?

  • Definition: Facts and statistics collected for reference or analysis.
  • Nature: Information in digital form suitable for processing and transmission.
  • Types:
  • Structured Data: Highly specific, stored in a predefined format.
  • Unstructured Data: Varied data stored in native formats.

Structured vs. Unstructured Data

  • Structured Data: Examples include CSV files.
  • Unstructured Data: Examples include images (PNG, JPG), audio (MP3), and video files (MP4).
  • Schema Diff:
  • Structured: Schema-on-write (data is organized when written).
  • Unstructured: Schema-on-read (data is organized when accessed).

What is Data Analysis?

  • Definition: The process of telling a story with data by identifying, cleaning, transforming, and modeling data to uncover meaningful insights.
  • Purpose: Supports decision-making by transforming data into reports and visualizations.

Key Components of Data Analysis

  • Tools & Techniques: To turn data into actionable business insights.
  • Goals:
  • Improve efficiency
  • Reduce costs
  • Increase revenue

Data Analysis Process

  1. Collection: Gathering raw data.
  2. Extract, Transform, Load (ETL) Process: Preparing data for analysis.
  3. Data Modeling: Structuring data into a usable format.
  4. Data Visualization & Storytelling: Communicating insights effectively.

What is Data Analytics?

  • Definition: Analyzing raw data to derive actionable insights, enabling informed business decisions.
  • Process: Encompasses data extraction, preparation, analysis, and storytelling.

Types of Data Analytics

  1. Descriptive Analytics: What happened in the past.
  • Purpose: Summarizes historical data.
  • Tools: Excel, Tableau, Power BI, Google Analytics.
  1. Diagnostic Analytics: Why did it happen?
  • Purpose: Investigates past events.
  • Tools: Tableau, Power BI, SAS.
  1. Predictive Analytics: What is likely to happen in the future?
  • Purpose: Forecasts future trends based on historical data.
  • Tools: Python, R, SAS.
  1. Prescriptive Analytics: What is the best course of action?
  • Purpose: Recommends actions based on predictions.
  • Tools: IBM Optimization tools, SAS, FICO.

Descriptive Analytics Explained

  • Function: Uses statistical tools to provide a summary of past behaviors.
  • Implementation: Utilizes basic statistics and visuals.
  • Application Examples:
  • Retail sales analysis.
  • Customer purchase patterns.
  • Key Tools: Excel, Google Analytics.

Diagnostic Analytics Explained

  • Function: Delves into data to find reasons behind trends.
  • Example: E-commerce analyzing cart abandonment rates.
  • Skills Needed: Data mining, pattern recognition.

Predictive Analytics Explained

  • Function: Uses historical data to predict future events.
  • Example: Seasonal sales forecasts.
  • Algorithm Types: Linear regression, decision trees.

Prescriptive Analytics Explained

  • Function: Suggests optimal actions based on insights.
  • Example: Google Maps calculating best routes considering traffic.
  • Skills Needed: Advanced analytics and optimization.

Summary of Data Analysis Types

  • Descriptive: Answers "What happened?"
  • Diagnostic: Answers "Why did it happen?"
  • Predictive: Answers "What is likely to happen?"
  • Prescriptive: Answers "What should be done?"

Data Analytics Workflow Process

  1. Data Preparation: Profiling and cleaning data for analysis.
  2. Data Modeling: Defining relationships between data tables.
  3. Data Analysis: Exploring data to find insights.
  4. Data Visualization: Presenting data in a clear and effective manner.

Software Tools Used in Data Analytics

  • Data Analysis Tools: Excel, Tableau, SQL Server, Python, R.
  • Data Visualization Tools: Power BI, Qlik, Google Data Studio.

References for Further Learning

  • Career Foundry
  • Data Science Training Resources