IMP 1 Om Forecasting

7/31/2019 IMP 1 Om Forecasting

1/22

FORECASTING METHODS


2/22

FORECASTING APPLICATIONS

Marketing.. Demand Forecasting, Marketshare, Trend in prices

Operations.. Material requirements, Material

and Labour costs, Idle time, Inventory,

Defective parts

Finance.. Cash flows, Expenses, Revenues,

Costs

Personnel.. Labour Turnover, Absenteeism..


3/22

DEMAND MANAGEMENT

Coordinate and Control all the sources ofDemand to

- Use Production system efficiently- Delivery on Time

Types of Demand- Dependent Demand : part of a

product

- Independent Demand : eitherinfluence

Demand or respond to

Demand


4/22

Demand Management

A

B(4) C(2)

D(2) E(1) D(3) F(2)

Independent Demand

Dependent Demand

Independent demand is uncertain. Dependent demand is certain.


5/22

PATTERNS OF DEMAND

Average Demand - steady requirement

TREND - LONG-RUN GENERAL MOVEMENTS INCREASINGOR DECREASING

SEASONAL - RECURRENT AND PERIODIC EVERY 12

MONTHS, EVERY HOUR CYCLICAL - CAUSED BY ECONOMIC EXPANSIONS AND

CONTRACTIONS, TECHNOLOGICAL, DEMOGRAPHICAL,

ETC. VERY HARD TO FORECAST

RANDOM - NO DISCERNIBLE PATTERN


6/22

Forecasting methods

Qualitative.. Where no data available, useful for new

products Time series.. Based on past data, use of computers for faster

processing

Causal.. Based on factors influencing demand e.g.

Advertisement, quality, competition, economic factors, Govt

policies..

Simulation.. Computer based, Interactive, Iterative..


7/228

Forecasting...Qualitative Methods

Grass Roots - Talk to Sales Force, Talk to

CustomersMarket Research - Surveys of Customers,

Experimental Test Markets

Panel Consensus - Bring in ExpertsExecutive Judgment - Surveys or Formal Input from

Executives

Historical Analogy - For New Products/ Technology,

Find a Similar ProductDelphi Method - Formal, Sequential Method of

Polling and Pooling Expert Opinions


8/22

Forecasting methods... Timeseries analysis

Simple Moving average : Neither growing nor declining,

w/o seasonal characteristics, e.g.items in inventory

Weighted Moving Average : More weightage to recent past..

.5/.3/.2, sales in a dept stores

Simple exponential smoothing :Accurate, easily

understandable, less computation, retail/wholesaletrade,services

Regression Analysis:useful for long-term forecasting offamily of products, past and future fall in a straight line

Trend Analysis


9/2214

Which Method to Choose ?

Pick a model based on:

1. Time horizon to forecast

2. Data availability

3. Accuracy required

4. Size of forecasting budget

5. Availability of qualified personnel

ASSUMPTION: THE PAST WILL REPEAT AND WE HAVEACCURATELY MODELED IT!


10/2218

In-Class Exercise

Week Demand

1 820

2 7753 680

4 655

5 620

6 600

7 575

Develop 3-week and

5-week moving

average forecasts fordemand.

Assume you only have

3 weeks and 5 weeksof actual demand data

for the respective

forecasts


11/22

19

In-Class Exercise (Solution)

Week Demand 3-Week 5-Week

1 820

2 7753 680

4 655 758.33

5 620 703.33

6 600 651.67 710.00

7 575 625.00 666.00


12/22

20

Weighted Moving Average

F=wA+wA+wA+...+t 1t-1 2t-2 3t-3 nt

w =1i

i=1

n

Determine the 3-period

weighted moving average

forecast for period 4.

Weights:

t-1 .5

t-2 .3

t-3 .2

Week Demand

1 650

2 678

3 7204


13/22

21

Solution

Week Demand Forecast

1 650

2 6783 720

4 693.4

F=.5(720)+.3(678).(4


14/22

22

In-Class Exercise

Determine the 3-period

weighted moving average

forecast for period 5.

Weights:

t-1 .7

t-2 .2t-3 .1

Week Demand1 820

2 775

3 680

4 655


15/22

23

Solution

Week Demand Forecast

1 820

2 775

3 680

4 655

5 672


16/22

25

Exponential Smoothing Example

W e e k D e m a n d

1 8 2 0

2 7 7 5

3 6 8 0

4 6 5 5

5 7 5 0

6 8 0 2

7 7 9 8

8 6 8 9

9 7 7 5

1 0

Determine

exponential

smoothing forecasts

for periods 2-10using =.10 and

=.60.

Let F1=A1


17/22

Week Demand 0.1 0.6

1 820 820.00 820.002 775 820.00 820.00

3 680 815.50 820.00

4 655 801.95 817.30

5 750 787.26 808.09

6 802 783.53 795.59

7 798 785.38 788.35

8 689 786.64 786.579 775 776.88 786.61

10 776.69 780.77

26The McGraw-Hill Companies, Inc., 1998Irwin/McGraw-Hill


18/22

35

Simple Linear Regression Model

b is similar to the slope. However, since it iscalculated with the variability of the data in

mind, its formulation is not as straight-

forward as our usual notion of slope

Yt = a + bx

0 1 2 3 4 5 x (weeks)

Y


19/22

36

Calculating a and b

a=y-bx

b=xy-n(y)(x)

x -n(x2 2

)


20/22

37

Regression Equation Example

Week Sales

1 150

2 1573 162

4 166

5 177

Develop a regression equation to predict sales

based on these five points.


21/22

Week Week*Week Sales Week*Sales

1 1 150 150

2 4 157 314

3 9 162 486

4 16 166 664

5 25 177 8853 55 162.4 2499

Average Sum Average Sum

b= xy-n(y)(x)x-n(x

=2499-5(162.4)(3) =

a=y-bx=162.4-(6.3)(3)=

2 2

) ()55596310.

143.538

The McGraw-Hill Companies, Inc., 1998Irwin/McGraw-Hill


22/22

y = 143.5 + 6.3t

135

140

145

150155

160

165

170175

180

1 2 3 4 5

Period

S

ales

Sales

Forecast

39The McGraw Hill Companies Inc 1998I i /M G Hill

IMP 1 Om Forecasting

Documents

Transcript of IMP 1 Om Forecasting