Planning and Forecasting (Part B

)

Eng. Ahmed Bakhsh

What is Forecasting?
• Process of predicting a future event • Underlying basis of all business decisions
– – – – Production Inventory Personnel Facilities

Sales will be $200 Million!

Types of Forecasts by Time Horizon
• Short-range forecast
– Up to 1 year; usually less than 3 months – Job scheduling, worker assignments

• Medium-range forecast
– 3 months to 3 years – Sales & production planning, budgeting

• Long-range forecast
– 3+ years – New product planning, facility location

Types of Forecasts
• Economic forecasts
– Address business cycle, e.g., inflation rate, money supply etc.

• Technological forecasts
– Predict rate of technological progress – Predict acceptance of new product

• Demand forecasts
– Predict sales of existing product

Planning and Forecasting

Forecasting

To predict/approximate what a certain future event or condition will be. One can forecast: Production levels Technological developments Needed manpower Governmental regulations Needed Funds Training needs Resource needs Sale levels.  The most critical information to forecast.

Seven Steps in Forecasting
• • • • • • • Determine the use of the forecast Select the items to be forecasted Determine the time horizon of the forecast Select the forecasting model(s) Gather the data Make the forecast Validate and implement results

Planning and Forecasting

Forecasting

Two types of information to forecast: Qualitative Information Quantitative Information

Planning and Forecasting

Forecasting

Qualitative Forecasting
Used when: Past data cannot be used reliably to predict the future. Technological trends Regulations When no past data is available, usually because the situation is very new. Entry into new markets Development of new products

Planning and Forecasting

Forecasting

Qualitative Forecasting Methods •Jury of executive opinion •Delphi Method •Sales Force Composite •Consumer Market Survey (User’s Expectations)

Jury of Executive Opinion
• Involves small group of high-level managers – Group estimates demand by working together • Combines managerial experience with statistical models • Relatively quick • ‘Group-think’ disadvantage

© 1995 Corel Corp.

Delphi Method
• Iterative group process • 3 types of people
– Decision makers – Staff – Respondents

Decision Makers Staff
(What will sales be? survey) (Sales?) (Sales will be 50!)

• Reduces ‘groupthink’

Respondents
(Sales will be 45, 50, 55)

Sales Force Composite
• Each salesperson projects his or her sales • Combined at district & national levels • Sales reps know customers’ wants • Tends to be overly optimistic
Sales

© 1995 Corel Corp.

Consumer Market Survey
• Ask customers about purchasing plans • What consumers say, and what they actually do are often different • Sometimes difficult to answer
How many hours will you use the Internet next week?

© 1995 Corel Corp.

Planning and Forecasting

Forecasting

Quantitative Information Used when data is tangible, can be used reliably to predict the future, and there is sufficient historical data upon which to base forecasts. Sales Profits Production levels

Quantitative Forecasting Methods
Quantitative Forecasting Time Series Models Associative Models

Moving Average

Exponential Smoothing

Trend Projection

Linear Regression

What is a Time Series?
• Set of evenly spaced numerical data
– Obtained by observing response variable at regular time periods

Forecast based only on past values
– Assumes that factors influencing past and present will continue influence in future

Example
Year: Sales: 1998 78.7 1999 63.5 2000 89.7 2001 93.2 2002 92.1

Time Series Components
Trend Cyclical

Seasonal

Random

Seasonal Component
• Regular pattern of up & down fluctuations • Due to weather, customs etc. • Occurs within 1 year
Respons e Summe r
© 1984-1994 T/Maker Co.

Mo., Qtr.

Common Seasonal Patterns
Period of Pattern Week Month Month Year Year Year “Season” Length Day Week Day Quarter Month Week Number of “Seasons” in Pattern 7 4–4½ 28 – 31 4 12 52

• Repeating up & down movements • Due to interactions of factors influencing economy • Usually 2-10 years duration
Cycle Response

Cyclical Component

Mo., Qtr., Yr.

Random Component
• Erratic, unsystematic, ‘residual’ fluctuations • Due to random variation or unforeseen events
– Union strike – Tornado
© 1984-1994 T/Maker Co.

• Short duration & nonrepeating

Product Demand Charted over 4 Years with Trend and Seasonality
Demand for product or service
Seasonal peaks Trend component

Actual demand line Average demand Rando over four m years variati Year Year on 2 3

Year 1

Year 4

Naive Approach
• Assumes demand in next period is the same as demand in most recent period
– e.g., If May sales were 48, then June sales will be 48

• Sometimes cost effective & efficient
© 1995 Corel Corp.

Moving Average
• Simple Moving Average Method • Weighted Moving Average Method

Planning and Forecasting

Forecasting

Quantitative Forecasting Methods 1. Simple Moving Average: Assumptions

Time series has a level and a random component only No Trend No seasonal or cyclical variations

1 n Fn +1 = ∑t =1 At n
n=current value A=actual value n+1 = forecast value for next

Moving Average Example
You’re manager of a museum store that sells historical replicas. You want to forecast sales (000) for 2003 using a 3-period moving average. 1998 4 1999 6 2000 5 2001 3 2002 7
© 1995 Corel Corp.

Moving Average Solution

Tim e

Moving Average Solution

Tim e

Moving Average Solution

Tim e

Moving Average Graph
Sales 8 6 4 2 95 96 97 98 Year
Actual Forecas t

99

00

Planning and Forecasting

Forecasting

Quantitative Forecasting Methods 2. Weighted Moving Average: Assumptions Used when trend is present Older data usually less important Weights based on intuition Often lay between 0 & 1, & sum to 1.0

Fn +1 = ∑t =1 wt At where
n

wt = 1 t =1

n

n=current value n+1 = forecast value for next A=actual value w=weight value

Planning and Forecasting

Forecasting

Quantitative Forecasting Methods 2. Weighted Moving Average:

Fn +1 = ∑t =1 wt At where
n
Example Period Actual Value 1999 2000 2001 2002 2500 1500 1000 500

wt = 1 t =1

n

Weights are (0.1, 0.2, 0.3, 0.4) respectively. Find Sales for the year 2003?

Planning and Forecasting

Forecasting

Quantitative Forecasting Methods 2. Weighted Moving Average:

Fn +1 = ∑t =1 wt At where
n
Solution Period Actual Value Weight 1999 2000 2001 2002 2500 1500 1000 500 0.1 0.2 0.3 0.4

wt = 1 t =1

n

F(2003) = 0.1*2500 + 0.2*1500 + 0.3*1000 + 0.4*500 F(2003) = 1050

Disadvantages of Moving Average Methods
• Increasing n makes forecast less sensitive to changes • Do not forecast trend well • Require much historical data • All data (in the simple moving average technique) are weighted equally and data which are too old to be included are weighted by zero

Planning and Forecasting

Forecasting

Quantitative Forecasting Methods 3. Exponential Smoothing Equations:

Fn +1 = Fn + α ( An − Fn )

= α An + (1 − α ) Fn
– Fn+1 – An = Forecast value = Actual value

−α

= Smoothing constant

(Use for computing forecast)

Exponential Smoothing Example
During the past 8 quarters, the Port of Baltimore has unloaded large quantities of grain. (α = .10). The first quarter forecast was 175.. Quarter Actual 1 2 3 4 5 6 7 8 9 180 168 159 175 190 205 180 182 ?

Find the forecast for the 9th quarter.

Exponential Smoothing Solution
Fn+ = Fn + 0.1(An 1
QuarterActual 1 2 3 4 5 6 180 168 159 175 190 205 175.00 +

Fn) Forecast, F N+1
(α = .10) 175.00 (Given)

Exponential Smoothing Solution
Fn+ = Fn + 0.1(An - Fn) 1
QuarterActual Actua 1 2 3 4 5 6 180 168 159 175 190 205 175.00 + .10( Forecast, F N+1 (α = .10) 175.00 (Given)

Exponential Smoothing Solution
Fn+ = Fn + 0.1(An - Fn) 1
QuarterActual 1 2 3 4 5 6 180 168 159 175 190 205 175.00 + .10(180 Forecast, FN+1 (α = .10) 175.00 (Given)

Exponential Smoothing Solution
Fn+ = Fn + 0.1(An - Fn) 1
Quarter Actual 1 2 3 4 5 6 180 168 159 175 190 205 Forecast, FN+1 (α = .10) 175.00 (Given) 175.00 + .10(180 - 175.00)

Exponential Smoothing Solution
Fn+ = Fn + 0.1(An - Fn) 1
Quarter Actual 1 2 3 4 5 6 180 168 159 175 190 205 Forecast, FN+1 ( α = .10) 175.00 (Given) 175.00 + .10(180 - 175.00) = 175.50

Exponential Smoothing Solution
Fn+ = Fn + 0.1(An 1
(α= .10) QuarterActual 1 2 3 4 5 6 180 168 159 175 190 205

Fn) Forecast, F N+1
175.00 (Given) 175.00 + .10(180 - 175.00) = 175.50 175.50 + .10(168 - 175.50) = 174.75

Exponential Smoothing Solution
Fn+ = Fn + 0.1(An 1 FForecast, n)
Actual Quarter 1995 1996 1997 1998 1999 2000 180 168 159 175 190 205 F N+1 (α= .10) 175.00 (Given) 175.00 + .10(180 - 175.00) = 175.50 175.50 + .10(168 - 175.50) = 174.75 174.75 + .10(159 - 174.75)= 173.18

Exponential Smoothing Solution
Fn+ = Fn + 0.1(An 1
(α= .10) Quarter Actual 1 2 3 4 5 6 180 168 159 175 190 205

Fn) Forecast, FN+1
175.00 (Given) 175.00 + .10(180 - 175.00) = 175.50 175.50 + .10(168 - 175.50) = 174.75 174.75 + .10(159 - 174.75) = 173.18 173.18 + .10(175 - 173.18) = 173.36

Exponential Smoothing Solution
Fn+ = Fn + 0.1(An 1
(α= .10) Quarter Actual 1 2 3 4 5 6 180 168 159 175 190 205

Fn) Forecast, F N+1
175.00 (Given) 175.00 + .10(180 - 175.00) = 175.50 175.50 + .10(168 - 175.50) = 174.75 174.75 + .10(159 - 174.75) = 173.18 173.18 + .10(175 - 173.18) = 173.36 173.36 + .10(190 - 173.36) = 175.02

Exponential Smoothing Solution
Fn+ = Fn + 0.1(An 1
Time Actual 4 5 6 7 8 9 175 190 205 180

Fn) Forecast, F N+1
(α= .10) 174.75 + .10(159 - 174.75) = 173.18 173.18 + .10(175 - 173.18) = 173.36 173.36 + .10(190 - 173.36) = 175.02 175.02 + .10(205 - 175.02) = 178.02

Exponential Smoothing Solution
Fn+ = Fn + 0.1(An 1
(α= .10) Time Actual 4 5 6 7 8 9 175 190 205 180

Fn) Forecast, F N+1
174.75 + .10(159 - 174.75) = 173.18 + .10(175 - 173.18) = 173.18 173.36 + .10(190 - 173.36) = 173.36 175.02 + .10(205 - 175.02) = 178.02 178.02 + .10(180 178.02)+ .10(182 178.22 = 178.22 178.22) = 178.58

18 ? 2

Impact of α
250 200 150 Actual Tonage 100 50 0 1 2 3 4 5 Q u a r te r 6 7 8 9 A c tual F o re c as t (0.5) F o re c as t (0.1)

Planning and Forecasting

Forecasting

Quantitative Forecasting Methods 3. Exponential Smoothing Same data assumptions as Moving Average It overcomes disadvantages of Moving Average. Forecast for current period is found as the forecast for the last period plus a proportion of the error made in the last forecast.

Planning and Forecasting

Forecasting

Quantitative Forecasting Methods 3. Exponential Smoothing Advantages: No waiting period before reliable forecasts can be calculated. It is only required to retain three figures for any forecast: the past forecast for current period, the current actual, and the smoothing constant. The value of can be made to change or adapt to changed circumstances, such as for example to make the series more sensitive to rapidly changing data

α