Chapter 4: Demand Forecasting Long Queue Traffic Congestion Stock Market Crash Forecasting Time Horizons Short Range Medium Range Long Range Has a time span of 1 year but Generally spans from 3 is generally less than 3 months to 3 years. months. 3 years or more in time span. Used for planning purchasing, job scheduling, workforce levels, job assignment, and production levels. Used in planning for new products, capital expenditures, facility location or expansion, and research and development. Useful in sales planning, production planning and budgeting, cash budgeting, and analysis of various operating plans. Types of Forecast Economic Technological Demand Address the business cycle by predicting inflation rates, money supplies, housing starts, and other planning indicators. Concerned with rates of technological progress, which can result in the birth of exciting new products, requiring new plants and equipment. Drive a company`s production, capacity, and scheduling systems and serve as an inputs to financial, marketing, and personal planning. Medium to Long Range Forecast Long Range Forecast Short Range Forecast Strategic Importance of Forecasting A good forecasts are of critical importance in all aspects of a business. Forecasts of demand therefore drive decisions in many areas that creates impact to product demand forecast of three activities: 1. Supply chain management 2. Human resources 3. Capacity Seven Steps in the Forecasting System Determine the use of the forecast Select the items to be forecasted Determine the time horizon of the forecast Select the forecasting model Gather the data needed to make the forecast Make the forecast Validate and implement the results Forecast Approach Executive Opinion Market Survey Qualitative Sales Force Composite Delphi Method Forecast Approach Naïve Approach Linear Regression Moving Average Quantitative Trend Projection Exponential Smoothing Kinds of Quantitative Methods Time Series Models A forecasting technique that uses a series of past data points to make a forecast. Such as naïve, moving average, and exponential smoothing. Associative Models A forecasting technique based on the development of an equation that summarizes the effects of predictor variables. Such as trend projection and linear regression. Decomposition of a Time Series Trend The gradual upward or downward movement of the data over time. Seasonality A pattern that repeats itself after a period of days, weeks, months, or quarters. Cycles Patterns in the data that occur every several years. Random Variations These are “blips” in the data caused by chance and unusual situations. Naive Approach A forecasting technique which assume that demand in the next period is equal to demand in the recent periods. Formula: Naïve = Demand in the recent periods Moving Average Approach A forecasting method that uses an average of the n most recent periods of data to forecast the next period. Formula: Moving Average = demand in previous 𝑛 periods 𝑛 Weighted Moving Average Approach Formula: ( Weight for period n demand in 𝑛 𝑝𝑒𝑟𝑖𝑜𝑑 … ) Weighted Moving Average = 𝑛 Exponential Smoothing Approach A weighted moving average forecasting technique in which data points are weighted by an exponential function. Formula: 𝐹𝑡 = 𝐹𝑡−1 +α(𝐴𝑡−1 −𝐹𝑡−1 ) Where: 𝐹𝑡 = New forecast 𝐹𝑡−1 = Previous periods forecast α = Smoothing constant 𝐴𝑡−1 = Previous period`s actual demand Measuring Forecast Error Formula: Forecast Error = 𝐴𝑡 −𝐹𝑡 Where: 𝐴𝑡 = Actual Demand 𝐹𝑡 = Forecast Value Mean Absolute Deviation A measure of the overall forecast error for a model. Formula: MAD = (Actual −Forecast) 𝑛 Mean Squared Error The average of the differences between the forecasted and observed values. Formula: MSE = (Forecast Error) 𝑛 2 Mean Absolute Percentage Error The average of the absolute differences between the forecast and actual values, expressed as a percent of actual values. Formula: MAPE = Actual −Forecast ∗100% Actual 𝑛 Trend Projection Approach A time series forecasting method that fits a trend line to a series of historical data points and then projects the line into the future for forecast. Formula: 𝑦= a + bx Where: 𝑦 = computed value of the variable to be predicted 𝑎= y-axis intercept b = slope of the regression line 𝑥 = the independent variable Trend Projection Approach Formula: b= 𝑥𝑦 −𝑛𝑥𝑦 𝑥 2 −𝑛𝑥 2 a = 𝑦 − 𝑏𝑥 Where: b = Slope a = Intercept = Summation sign x = known values of the independent variables 𝑦 = known values of the dependent variables 𝑥 = average of the x values 𝑦 = average of the y values n = number of data points or observations Exponential Smoothing with Trend Adjustment Approach Formula: 𝐹𝑡 = α(At−1)+(1−α)(Ft−1 +Tt−1 ) 𝑇𝑡 = ẞ(Ft −Ft−1 )+(1- ẞ) Tt−1 𝐹𝐼𝑇 = Ft + Tt Where: 𝐹𝑡 = Exponentially smoothed forecast average of the data series in period t 𝑇𝑡 = Exponentially smoothed trend in period t 𝐴𝑡 = Actual demand in period t α = Smoothing constant for the average (0 ≤ α ≤ 1) ẞ = Smoothing constant for the trend (0 ≤ ẞ ≤ 1) Seasonal Variations A regular upward or downward movements in a time series that tie to recurring events. Formula: Average Monthly Demand = Seasonal Index = 𝑇𝑜𝑡𝑎𝑙 𝐴𝑣𝑒𝑟𝑎𝑔𝑒 𝐴𝑛𝑛𝑢𝑎𝑙 𝐷𝑒𝑚𝑎𝑛𝑑 12 𝑚𝑜𝑛𝑡ℎ𝑠 𝐴𝑣𝑒𝑟𝑎𝑔𝑒 𝑀𝑜𝑛𝑡ℎ𝑙𝑦 𝐷𝑒𝑚𝑎𝑛𝑑 𝑓𝑜𝑟 𝑝𝑎𝑠𝑡 3 𝑦𝑒𝑎𝑟𝑠 𝐴𝑣𝑒𝑟𝑎𝑔𝑒 𝑀𝑜𝑛𝑡ℎ𝑙𝑦 𝐷𝑒𝑚𝑎𝑛𝑑 Correlation Coefficient for Regression Lines A measure of the strength of the relationship between two variables. Formula: r= 𝒏 𝒙𝒚− 𝒙 𝒚 𝒏 𝒙𝟐 −( 𝒙)𝟐 𝒏 𝒚𝟐 −( 𝒚)𝟐