Business Analytics and Data Science Fundamentals

Key Areas of Business Analytics

• Business Intelligence (BI): Tools and systems that play a key role in the strategic planning process of the corporation.

• Information Systems (IS): Systems for managing operational data.

• Statistics: Provides foundational techniques for data analysis.

• Operations Management (OM): Focuses on managing and optimizing production and operations.

• Data Mining: Techniques for extracting useful information from large datasets.

• Simulation: Modeling of real-world systems to predict outcomes under different scenarios.

• Risk Analysis: Evaluation of risks associated with decisions or operations.

Decision Support Systems (DSS)

• Utilized by major corporations.

• Typically involves a paid subscription for continuous updates.

• Provides crucial data management resources.

Data Visualization

• Chapter 3: Data Visualizations is emphasized.

• Importance of creating visual representations of data for analysis.

• Courses focusing on data visualization may also be available.

Software Support and Usage

• Spreadsheets: Widely used in the class, available via BlazeView or Pearson.

• Databases: Access to data sources is facilitated through platforms available for course use.

• Commercial Software: Various software available such as Excel and optional tools like Stack Crunch for statistical analysis.

Triad of Data Analytics Terms

Definitions and Importance

• Descriptive Analytics: Utilizes past and current data to describe what is happening.

  • Example: Performance tracking of an organization based on historical data.

• Predictive Analytics: Involves forecasting future outcomes based on historical data.

  • Analogy: Often referred to as a "crystal ball"; e.g., predicting future sales based on past behavior.

  • Extrapolation: A method to predict future behavior based on past data patterns.

• Prescriptive Analytics: Recommends actions based on data analysis.

  • Aim: To identify the best alternatives to maximize or minimize objectives like cost, productivity, or profit.

Example Scenario - Department Store Inventory

• End of season sales scenario requiring price reduction analysis to maximize revenue.

  • Descriptive: Analyze past data to determine when to reduce prices.

  • Predictive: Predict future sales at various price points based on past data.

  • Prescriptive: Recommend optimal pricing strategies for maximizing revenue.

Data and Information

• Data: Raw facts recorded on spreadsheets.

• Information: Insights gained from analyzing data.

• The relationship is summarized as data leading to information.

Examples of Data Sources

• Company annual reports.

• Web behavior: page views, time spent, product reviews, and more.

Big Data

Definition and Characteristics

• Defined as massive quantities of business data.

• Key attributes:

  • Volume: Large amounts of data.

  • Variety: Diverse data sources.

  • Velocity: Real-time data processing capability.

  • Veracity: Addressing uncertainty and unpredictability of data.

Impacts of Big Data

• Potential for economic transformation and competitiveness.

• Significance for organizations in enhancing consumer experience and operational excellence.

Reliability and Validity

Definitions

• Reliability: Consistency and accuracy of measurements.

  • Example: A weight scale showing consistent readings.

• Validity: The degree to which a measure accurately indicates what it is supposed to measure.

  • Example: A scale measuring weight (valid) but not measuring temperature (not valid).

Examples

1. Tire Pressure Gauge: Reliable but with inaccurate readings (valid).

2. Call Center Activity: Reliable in measurement but not valid for customer dissatisfaction.

3. Restaurant Survey: Quality of food is subjective, thus affecting reliability and validity.

Models in Data Analytics

Overview of Models

• Models can take multiple forms: verbal, visual, or mathematical.

Example: Product Life Cycle

1. Description: Product introduction leads to slow sales growth, followed by rapid growth, saturation, and eventual decline.

2. Visual Representation: Graph illustrating sales performance over time.

3. Mathematical Model: Provides mathematical framework for predicting sales.

   • Example formula: Sales = S, Time = T, with E, a, b, c as constants governing the model's behavior.

Decision Models

Components

• Inputs: Data, uncontrollable inputs (e.g., interest rates, inflation), and controllable decision options.

  • Example: Price, product features, promotional strategies.

• Outputs: Performance measures like revenue, profit, and customer satisfaction.

Examples of Performance Measures

• Revenue and Profitability: Core measures for assessing success in business.

• Customer Satisfaction: Important, especially for non-profit organizations.

• Productivity: Assessing the efficiency in achieving organizational goals.

Descriptive and Predictive Models

Descriptive Models

• Focus on past data for analyzing current situations and potential outcomes.

• Example: Calculating fuel consumption based on driving habits, where total gallons consumed is derived from miles driven and miles per gallon.

Predictive Models

• Example: Outsourcing costs versus in-house production costs.

  • Breakeven Analysis: Equating total costs of different production methods to find the volume at which costs are equal.

  • Example equation to equate costs:
    $TC<em>{in-house} = TC</em>{outsourcing}$.

  • At 1,000 units produced, costs will be the same for both methods.