Week 11 Summary

Forecasting Overview

  • Definition: Process of predicting future events; essential for business decisions.

Importance of Forecasting

  • Provides competitive advantage (e.g., Disney).

  • Informs labor management, operations, scheduling.

  • Inputs: GDP, rates, travel statistics, customer surveys.

Forecasting Time Horizons

  • Short-range: Up to 1 year (e.g., job scheduling).

  • Medium-range: 3 months to 3 years (e.g., budgeting).

  • Long-range: Over 3 years (e.g., product development).

Types of Forecasts

  • Economic: Business cycles, inflation, etc.

  • Technological: Rate of tech progress.

  • Demand: Sales predictions of products/services.

The Strategic Importance of Forecasting

  • Impacts HR decisions, capacity management, supply chain management.

Seven Steps in Forecasting Systems

  1. Determine forecast use.

  2. Select items to forecast.

  3. Determine time horizon.

  4. Choose models.

  5. Gather data.

  6. Make forecast.

  7. Validate/implement results.

Forecasting Approaches

  • Qualitative: Used for vague situations (new tech/products).

  • Quantitative: Used for stable situations (existing products).

Forecasting Methods

  • Qualitative Methods: Jury of executive opinion, Delphi method, market surveys.

  • Quantitative Methods: Time-series models, regression analysis.

Components of Demand

  • Trend: Long-term direction (years).

  • Seasonal: Regular fluctuations (within a year).

  • Cyclical: Business cycle-related (multiple years).

  • Random: Unpredictable variations (short durations).

Common Techniques

  • Naive Method, Moving Average, Weighted Moving Average, Exponential Smoothing.

Error Measurement

  • Mean Absolute Deviation (MAD).

  • Mean Squared Error (MSE).

  • Mean Absolute Percent Error (MAPE).

Linear Trend Projection

  • Use least-squares for predicting values based on historical data.

Seasonal Forecasting

  • Adjust for seasonal variations; calculate seasonal indices.

Associative Forecasting

  • Regression and correlation analysis to predict values using multiple variables.

Monitoring Forecasts

  • Use tracking signals to measure accuracy; bias detection if consistently high/low.

Special Considerations

  • Unique challenges in service sector forecasting; need for short-term records; variability by industry.