Data Analytics: Lessons 1 & 2 Overview

Lesson 1: What is Data Analytics?

• Data: Raw, unorganized facts that require processing to be meaningful.

• Data Analysis: The process of collecting, organizing, and interpreting raw data to find patterns and insights. Focuses on historical data to answer "what" and "why" questions.

• Techniques: Descriptive statistics, correlation analysis, hypothesis testing.

• Tools: Excel, SPSS, R, Python (Pandas) are used

• Data Analytics: Broader than data analysis, including descriptive, diagnostic, predictive, and prescriptive analytics. Uses advanced tools and methods (e.g., machine learning) to forecast future outcomes.

• Tools: Python, R, Tableau, Power BI, SQL, Hadoop, Spark, AWS, Google Cloud are used.

• Key Difference: Data analysis focuses on interpreting existing data; data analytics encompasses the entire process of planning, analyzing, and predicting future outcomes.

Lesson 2: The Analytics Process

• 6 Steps of the Analytics Process:

  • Problem Definition: Clearly defining the problem and objectives.
  • Data Collection: Gathering relevant data from reliable sources.
  • Data Preparation/Cleaning: Cleaning and organizing data for analysis (handling missing data, outliers).
  • Data Analysis: Uncovering patterns, trends, and insights in the data.
  • Interpretation of Results: Translating analysis into actionable insights.
  • Implementation and Iteration: Applying findings, monitoring results, and improving the process.

• Life Cycle of Analytics (CRISP-DM): Business Understanding → Data Understanding → Data Preparation → Modeling → Evaluation → Deployment.

Lesson 3: Types of Analytics

• 4 Types of Analytics:

  1. Descriptive Analytics: Summarizes historical data to identify patterns/trends. (e.g., tracking daily customer visits) Techniques: Data aggregation, summarization, visualization.
  2. Diagnostic Analytics: Examines historical data to discover root causes of outcomes. (e.g., investigating reasons for increased customer complaints) Techniques: Drill-down analysis, statistical analysis (correlation, regression).
  3. Predictive Analytics: Uses historical data to predict future outcomes or trends. (e.g., forecasting sales for the next quarter) Techniques: Machine learning, time series analysis, predictive modeling.
  4. Prescriptive Analytics: Recommends actions to optimize outcomes based on predictions. (e.g., optimizing delivery routes to reduce costs) Techniques: Optimization algorithms, decision trees, simulation models.

Lesson 4: Importance of Analytics

• Importance of Analytics:
  • Informed Decision-Making: Providing evidence-based insights.
  • Problem Solving: Identifying trends, patterns, and anomalies.
  • Efficiency and Optimization: Improving productivity and resource allocation.
  • Competitive Advantage: Predicting market trends and understanding customer needs.
  • Risk Management: Anticipating and mitigating potential risks.

Lesson 5: Overview of Analytics Tools and Technologies

• Key Analytics Tools:

  • Microsoft Excel: Spreadsheet software for data wrangling, reporting, and visualization.
  • Python: Programming language for data analysis, machine learning, and web scraping.
  • R: Programming language for statistical analysis and data visualization.
  • Microsoft Power BI: Business analytics service for data visualization and reporting.
  • Tableau: Data visualization tool for interactive dashboards and data storytelling.
  • SPSS: Statistical software for data management, statistical analysis, and reporting.
  • KNIME: Open-source analytics platform for data integration, reporting, and machine learning.
  • Weka: Machine learning and data mining software for data preprocessing, classification, and clustering.

• Analytics Tools by Type:

  • Descriptive Analytics: Excel, Google Sheets, Tableau, Power BI.
  • Diagnostic Analytics: SPSS, Python, R, Tableau, Power BI.
  • Predictive Analytics: Excel (basic), Scikit-learn (Python), caret (R), Google AutoML, AWS Forecast.
  • Prescriptive Analytics: Solver in Excel, Salesforce Einstein.