Forecasting

Trend Analysis

• Importance of accurate demand prediction to avoid shortages or excess inventory.

Consequences of Forecasts

• Underestimating demand leads to shortages.

• Overestimating demand results in surplus inventory that may need to be sold at a loss.

Demand Prediction Methods

• Qualitative Methods:

• Expert opinions (sales teams).

• Market research.

• Quantitative Methods:

• Moving averages (simple, weighted).

• Exponential smoothing.

• Regression analysis (linear).

Types of Trends

• Linear increasing, decreasing, or non-linear patterns.

• Seasonal patterns (e.g., ice cream sales peak in summer).

• Cyclical patterns influenced by economic conditions.

• Irregular variations caused by unexpected events (e.g., COVID-19).

Importance of Demand Patterns

• Helps in predicting future demand and identifying market opportunities while managing risks.

Forecasting Techniques Introduction

• Simple Moving Average (SMA):

• Smooths out data fluctuations for trend identification.

• Focuses on recent data for better predictions.

• Calculation of the moving average involves averaging a specific number of recent observations.

Forecasting Error

• Forecasting Error: Difference between observed and forecasted values.

• Mean Absolute Deviation (MAD) and Mean Squared Error (MSE):

• MSE: average of squared differences from the mean.

• MAD: average absolute differences.

• Lower value indicates better accuracy.

Absolute Percentage Error (APE)

• APE = (Absolute Error / Actual Outcome) * 100%

• Offers a clear picture of forecasting accuracy.

Practical Application

• Forecasting demand using historical data to identify optimal moving average techniques based on measurement errors.

Seasonal Index Calculation

• Use seasonal indices to adjust forecasts based on historical seasonal demand patterns.

• Average annual demand can be divided by seasonal indices to determine expected demand in each season.