Untitled Flashcards Set

Chapter 7: Machine Learning and Deep Learning

• AI Overview: AI mimics human intelligence using Machine Learning (ML) and Deep Learning (DL).

  • ML: Learns from data and adapts; includes supervised (e.g., regression, classification) and unsupervised (e.g., clustering) learning.

  • DL: Advanced ML using neural networks with input, hidden, and output layers; used in tasks like self-driving cars.

• Applications: Includes SEO, PPC bidding, and clustering (e.g., Uber).

• AI Types: Applied AI for specific tasks (e.g., autonomous driving) and General AI for varied tasks.

Chapter 8: Cloud Services

• Definition: Cloud computing delivers internet-based services (e.g., storage, servers).

• Models: Public (shared), Private (dedicated), Hybrid (mixed).

• Service Types:

  • IaaS: Infrastructure (e.g., AWS EC2).

  • PaaS: Development platforms (e.g., Google App Engine).

  • SaaS: Software applications (e.g., Salesforce).

• Benefits: Scalability, accessibility, cost-effectiveness, and real-time processing.

• Challenges: Security perceptions, cost management, compliance issues.

• Applications: Cloud tools support data integration, analysis, and sharing.

Chapter 9: Web Analytics

• Definition: Measures web data for optimization.

• Key Metrics: Users (total, active, new), sessions, pageviews, conversions, bounce rate.

• Google Analytics 4 (GA4): Tracks user behavior, acquisition, and interactions.

• SEO Support: Tracks organic visitors and refines keyword strategies.

Chapter 11: Storytelling through Visualization

• Data Visualization:

  • Simplifies data insights using graphs/charts.

  • Key types: Bar, line, pie, scatter plots, and advanced visuals (e.g., tree maps).

  • Benefits: Enhances decision-making and identifies trends.

• Tools: Tableau, Excel, R, Python.

• Preparation: Clean data, define objectives, and choose appropriate visuals.

Chapter 12: Predictive Analytics with Regression

• Definition: Forecasts outcomes based on historical data.

• Techniques:

  • Linear regression (simple and multiple).

  • Key metrics: R², Adjusted R², and P-values.

• Applications: Predicts trends, customer behavior, and sales.

• Challenges: Requires robust datasets and continuous updates for accuracy.

Chapter 13: Prescriptive Analytics with Optimization

• Definition: Provides actionable recommendations by solving optimization problems.

• Key Elements:

  • Objective function, decision variables, constraints.

  • Types: Discrete vs. continuous, constrained vs. unconstrained.

• Applications: Supply chain, resource allocation, marketing strategies.

• Approaches: Deterministic (fixed parameters) and stochastic (uncertain parameters).

Challenges: Data quality, computational complexity, dynamic environments.