Loengud
Module 1: Analytics Foundations
- Data analytics in the age of AI
- Analytics landscape and maturity models
- Framing business problems analytically
- Data types, sources, quality
Module 2: Python & Cloud Environments
- Python for business analytics
- Google Colab setup and features
- Core libraries: pandas, numpy, matplotlib, seaborn
- Data import/export, reproducibility
Module 3: Data Visualization & Storytelling
- Principles of effective visualization
- Choosing the right chart
- Visual perception and cognitive load
- Avoiding misleading visualizations
- Dashboard design for different audiences
- Data storytelling frameworks
- Communicating uncertainty
Module 4: Statistical Thinking
- Descriptive statistics and distributions
- Hypothesis testing and confidence intervals
- Correlation vs. causation
- Statistical significance vs. practical significance
- Common statistical pitfalls
Module 5: Predictive Modeling I - Regression
- Multiple regression and feature selection
- Logistic regression for classification
- Model evaluation: training/test split, cross-validation
- Regularization and overfitting prevention
Module 6: Predictive Modeling II - Classification
- Decision trees and interpretation
- Random forests and ensemble methods
- Model performance metrics (accuracy, precision, recall, ROC)
- Feature importance
- Business applications: churn, fraud, lead scoring
Module 7: Clustering & Segmentation
- K-means clustering
- Hierarchical clustering
- Cluster evaluation and interpretation
- Customer segmentation strategies
- Targeting and personalization
Module 8: Time Series & Forecasting
- Time series components (trend, seasonality)
- Forecasting methods (moving averages, exponential smoothing)
- Demand planning and inventory optimization
- Forecast accuracy metrics
Module 9: AI in Business Analytics
- AI in analytics: definitions and capabilities
- Augmented analytics: human-AI collaboration
- Automation: when machines act independently
- Generative AI for reports, code, and insights
- AI agents: autonomous multi-step workflows
- Benefits and risks of AI-driven analytics
- Human-in-the-loop system design
- Governance, transparency, and accountability
Module 10: Integrating Analytics into Organizations
- Analytics as strategic capability
- Aligning analytics with corporate strategy
- Operating models (centralized, decentralized, hybrid)
- Change management and adoption
- Building data-driven culture
- Talent, skills, and training
- Measuring and communicating business impact