Ch.9 Forecasting

Question 1

An estimate of the future level of some variable, used to predict future event, and determine
- Long-term Capacity Needs
- Yearly Business Plans
- Short-term OSC Activities

Answer 1

Forecasting

Question 2

3 Common Forecast Types

Answer 2

1. Demand
   Overall market / Firm-level
2. Supply
   # of current suppliers/supply aggregated/tech & political trends
3. Price
   $ of key materials & srv

Question 3

Underlying basis of all business decisions

Answer 3

• Production
• Inventory
• Personnel
• Facilities

Question 4

Forecasting Time Horizons

Answer 4

1. Short-range
   3 mo. to 1 yr
   more accurate
   purchasing/job schedule/workforce lvl/job assgmt/production lvl
2. Medium-range
   3 mo. to 3 yrs
   sales & production planning/budgeting
3. Long-range
   3+ yrs
   new product planning/facility location/r & d

Question 5

In product life cycle (Intro/Growth/Maturity/Decline), which require longer forcasts?

Answer 5

Intro & Growth

Question 6

As product passes thru life cycle, forecasts are useful in projecting

Answer 6

• Staffing levels
• Inventory levels
• Factory Capacity

SIF

Question 7

4 Laws of Forecasting

Answer 7

Law1: Almost always Wrong
Law2: Near term Accurate↑
Law3: Groups of G/S Accurate↑
all cars vs green cars
Law4: No Substitute for calculated values

Question 8

Features of Forecasts

Answer 8

1. Causal system assumed
2. Randomness makes forecast imperfect
3. Accurate for Groups
4. Time Horizon↑Accuracy↓

Question 9

Select Forecasting Method if

based on intuition/informed opinion & little data

Answer 9

Qualitative techniques

Question 10

Select Forecasting Method if

use measurable/historical data

Answer 10

Quantitative techniques

Question 11

5 Qualitative techniques

Answer 11

1. Market Surveys
   questionnaires solicit/time+$ ↑
2. Build-up
   expert familiar w/ mkt segment
3. Life Cycle Analogy
   for new G/S
4. Panel Consensus
   experts work together
5. Delphi
   experts work individually → modify w/ shared info

MLBPD

Question 12

2 Quantitative models
& subs

Answer 12

1. 時序Time series models
   a. Last Period
   b. Moving Avg
   c. Weighted Moving Avg
   d. Exponential Smoothing
   e. Linear Regression
2. 因果Causal models
   a. Linear Regression
   b. Multiple Regression

Question 13

A class of
Quantitative Forecasting
modeled as function
other than time

Answer 13

Causal Forecasting models

e.g. Variable/Cause
Drought relief/Rainfall
Refinancing/Interest rates
Food eaten/# of guests

Question 14

3 Major Questions for Life Cycle Analogy method

Answer 14

1. How Long for each stage?
2. How Rapid Growth/Decline be?
3. How Large is Overall/Maturity ph. Demand?

Question 15

Demand Patterns of
Time Series Forecast

Answer 15

1. Randomness
   Unpredictable movement
2. Trend
   long-term movement
3. Seasonality
   repeated spike/drop

Question 16

Current Demand
= Forecast Next Period

Time Series/Quantitative

Answer 16

Last Period model

Question 17

Average of a Set of Recent Values generates smoothed forecast

Time Series/Quantitative

Answer 17

Moving Average model
(or Smooting model)

x-Period : avg of prev x period data
random↑⇒smooth/delay↑: for x↑

Question 18

Forecast @next period =
Weighted Avg Value & Forecast @current period

Answer 18

Exponential Smoothing model

F₂=αD₁ + (1-α)F₁
0≤α ≤1 (smoothing constant)
random ↑ ⇒ α ↓

Question 19

Adjusted Exponential Smoothing model

Answer 19

AF₂ = F₂+T₂

AF₂ : Adj. Fc @next period
F₂ : UnAdj. Fc @next period
= αD₁+ (1-α)F₁
T₂ : Trend Factor @next period
= β(F₂-F₁) + (1-β)T₁
T₁ : Trend Factor @curr. period
β : Smoothing Constant for Trend Factor

Question 20

Forecast Variables expressed as Linear Function or independent variable

Causal/Quantitative

Answer 20

Linear Regression

y=a+bx

a: intercept term=
b: slope coefficient (trend)
x: independent variable
(x₀ = mean x)
y: forecast (dependent)
(y₀ = mean y)

        ∑xy - [ (∑x∑y)/n ] b=----------------------
         ∑x² - [ (∑x)² / n ]

Question 21

4 Steps to develop
Seasonality Adjustments

Answer 21

1. Unadjusted forecast model
2. Ratio of “Demand÷Forecast”
   ∙ if Ratio<1 ⇒ OverForecasted
   ∙ if Ratio>1 ⇒ UnderForecasted
3. Seasonal Index (si)
   = Ratio (in Mo.s or Qtrs)
4. Adjusted Forecast model
   = si × Unadjusted

Question 22

FE

Forecast Error
Fc Accuracy Measure

Answer 22

= Demand - Forecast

= D-F

Question 23

MFE

Mean Forecast Error
Fc Accuracy Measure

Answer 23

= ∑FE / n

= ∑(D-F)/n

Measures bias/propensity of model to under-/over- forecast
(unbiased if MFE=0, even having large errors)

Question 24

AD

Absolute Deviation
Fc Accuracy Measure

Answer 24

= |FE|

= |D-F |

Question 25

MAD

Mean Abs. Deviation
Fc Accuracy Measure

Answer 25

= ∑AD / n = ∑|FE| / n

= ∑|D-F |/n

Tracks Avg Size of Errors (≥0)

Question 26

MAPE

Mean Abs. % Err.
Fc Accuracy Measure

Answer 26

= ∑|FE/D| / n (%)

=∑|(D-F)/D |/ n
=∑(AD/D) / n

Indicate Error Magnitude using abs. value of FE

Question 27

PE

Percentage Error
Fc Accuracy Measure

Answer 27

= FE / D (%)

= (D-F)/D

Question 28

Tracking Signal

Fc Accuracy Measure

Answer 28

= ∑FE / MAD

= ∑(D-F) / ∑|D-F|/n

Flag if model out of control
Normal if -4 ⇔ 4

Question 29

__ used to develop/evaluate/change Fc models
& select best model fits past data

Answer 29

Computer-Based Forecasting Packages

Question 30

__ is business processes w/ IT support, SC partners agree to
∙ mutual objectives & measures
∙ develop joint sales & operational plans
∙ collaborate on sales Fc & replenish plans

Answer 30

CPFR

Collaborative Planning, Forecasting, & Replenishment

Collaboration is emphasized & distinguished from traditional approaches