module 8: Production Planning

1.Forecasting

Back to main index exit back to module contents

 module 8: Production Planning

FORECASTING

Forecasting is essential for a number of

planning decisions

LONG TERM DECISIONS

 New Product Introduction
 Plant Expansion

Back to main index exit back to module contents

 module 8: Production Planning

MEDIUM TERM DECISIONS

 Aggregate Production Planning

 Manpower Planning

 Inventory Policy

SHORT TERM DECISIONS

 Production planning

 Scheduling of job orders

Back to main index exit back to module contents

 module 8: Production Planning

PLANNING PROCESS
A Forecast of Demand is an essential Input for
Planning
System
Objectives

Demand System to be Plan of

Forecast Managed Action
Constraints
- Budget / Space
Resources
- Men
- Equipment

Back to main index exit back to module contents

 module 8: Production Planning

METHODS OF FORECASTING
(a) Subjective or intuitive methods
 Opinion polls, interviews
 DELPHI

(b) Methods based on averaging of past data

 Moving averages
 Exponential Smoothing

Back to main index exit back to module contents

 module 8: Production Planning

(c) Regression models on historical data

 Trend extrapolation

(d) Causal or econometric models

(e) Time - series analysis using stochastic

models
 Box Jenkins model

Back to main index exit back to module contents

 module 8: Production Planning

FORECASTING
 Objective
 Scientific
 Free from ‘BIAS’
 Reproducible
 Error Analysis Possible

PREDICTION
 Subjective
 Intuitive
 Individual BIAS
 Non - Reproducible
 Error Analysis Limited

Back to main index exit back to module contents

 module 8: Production Planning

COMMONLY OBSERVED
“NORMAL” DEMAND
PATTERNS
Constant Linear
Trend
D
D

t t

Back to main index exit back to module contents

 module 8: Production Planning

D Seasonal
D
Cyclic Pattern with
Growth
t t

Back to main index exit back to module contents

 module 8: Production Planning

ABNORMAL DEMAND
PATTERNS

Transient Sudden Sudden

Impulse Rise Fall

Back to main index exit back to module contents

 module 8: Production Planning

OPINION POLLS
Personal interviews
e.g. aggregation of opinion of sales representatives to
obtain sales forecast of a region
 Knowledge base (experience)
 Subjective bias
Questionnaire method
 questionnaire design
 choice of respondents
 obtaining respondents
 analysis and presentation of results (forecasting)
Telephonic conversation
 Fast
DELPHI

Back to main index exit back to module contents

 module 8: Production Planning

DELPHI
A structured method of obtaining responses from
experts.
Utilizes the vast knowledge base of experts
Eliminates subjective bias and ‘influencing’ by
members through anonymity
Iterative in character with statistical summary
at end of each round (Generally 3 rounds)
Consensus (or Divergent Viewpoints)
usually emerge at the end of the exercise.

Back to main index exit back to module contents

 module 8: Production Planning

Expert 1

Coordinator Expert 2

Expert n

A Statistical
• Mean summary
•Median can be given
1990 1995 2000 2005 2010 •Std. deviation at end of
year
each round

Back to main index exit back to module contents

 module 8: Production Planning

DELPHI (Contd.)
Round
1
Moving
Towards
Consensus Round
2

Round
3

Back to main index exit back to module contents

 module 8: Production Planning

DELPHI (Contd.)
Round
1
Moving
Towards
Divergent
View Points Round
2

Round
3

Back to main index exit back to module contents

 module 8: Production Planning

MOVING AVERAGES
Month Demand 3 Month MA 6 Month MA

Jan 199
Feb 202
Mar 199 200.00
Apr 208 203.00
May 212 206.33
Jun 194 203.66 202.33
Jul 214 205.66 207.83
Aug 220 208.33 210.83
Sep 219 216.66 213.13
Oct 234 223.33 217.46
Nov 219 223.00 218.63
Dec 233 227.66 225.13
Back to main index exit back to module contents
 module 8: Production Planning

K PERIOD MA = AVERAGE OF K MOST

RECENT OBSERVATIONS

For instance : 3 PERIOD MA FOR MAY

= Demands of Mar, Apr, May
/3
= (199 + 208 + 121) / 3 =
206.33

Back to main index exit back to module contents

 module 8: Production Planning

CHARACTERISTICS OF
MOVING AVERAGES

Dt Dt

t t

(1) MOVING AVERAGES LAG A TREND

Back to main index exit back to module contents

 module 8: Production Planning

Dt

(2) MOVING AVERAGES ARE OUT OF PHASE

FOR CYCLIC DEMAND

Back to main index exit back to module contents

 module 8: Production Planning

Dt

(3) MOVING AVERAGES FLATTEN PEAKS

Back to main index exit back to module contents

 module 8: Production Planning

EXPONENTIAL SMOOTHING
Ft = one period ahead forecast made at
time time t
Dt = actual demand for period t
 = Smoothing constant (between 0 & 1)
(generally chosen values tie between
0.01 and 0.3)
Ft = Ft-1 +  (Dt - Ft-1)

Back to main index exit back to module contents

 module 8: Production Planning

MOVING AVERAGES
AND
EXPONENTIAL SMOOTHING

(Equivalence between  & N :)

 = 2 / (N+1)

Back to main index exit back to module contents

 module 8: Production Planning

230
 = 0.3
220

3 Month
210  = 0.1
MA

200 6 Month
MA
190
J F M A M J J A S O N D J
Month

Back to main index exit back to module contents

 module 8: Production Planning

Common Regression Functions

Linear
dt

t
dt’ forecast
dt actual demand (for time period t)
dt’ = a + bt (parameters a, b)

Back to main index exit back to module contents

 module 8: Production Planning

Cyclic

dt

dt’ = a + u Cos (2/n)t + v Sin (2/n)t (parameters a,

u, v)

Back to main index exit back to module contents

 module 8: Production Planning

Cyclic with
dt Growth

dt’ = a +bt + u Cos (2/n)t + v Sin (2/n)t (parameters

a,b,u, v)

Back to main index exit back to module contents

 module 8: Production Planning

Quadratic
dt

t
dt’ = a +bt + ct2 (parameters a,b,c)

Parameters Determined by
Minimizing the Sum of Squares of
errors,
Back to main index exit back to module contents
 module 8: Production Planning
246
REGRESSION 232

230 Actual
Data 218
220
Ft = 193 + 3t
(Regression Line)
210

200 Forecast
for next
JAN
190
J F M A M J J A S O N D J Month (t)
1 2 3 4 5 6 7 8 9 10 11 12 13
Back to main index exit back to module contents
 module 8: Production Planning

Standard error of estimate = n  (Dt - Ft)2

t=
Where 1 n-f
Dt = actual demand for period t = 7.32
Ft = forecast for period t
n = no. of data points
f = degrees of freedom lost (2 in this case)
95 % confidence limits for forecast of next
JAN ~ 232  14 (* 2 sigma)
Back to main index exit back to module contents
 module 8: Production Planning

CAUSAL MODELS
Here demand is related to
Causal variables
 GNP
 Per Capita income
 Consumer Price index
 …………
Demand for tyres
= f (Production of new automobiles,
Replacements by existing autos, Govt
policy on automobiles, …..)
Back to main index exit back to module contents
 module 8: Production Planning

Dt =  Pt +  Pt-5 + 
could be a simplified causal model
(Here parameters  , ,,  are estimated by
regression from data)
For a Causal Model to be Useful
The causal variables should be
Leading
Highly correlated with the variable of interest

Back to main index exit back to module contents

 module 8: Production Planning

TIME SERIES ANALYSIS

Time series decomposed into
 Trend
 Seasonality
 Cycle
 Randomness
And Forecast generated from these
components

Back to main index exit back to module contents

 module 8: Production Planning

Stochastic modelling ( Box

and Jenkins)
Various processes eg.
 Autoregressive (AR) order p
 Moving average (MA) order q
 ARMA order (p,q)
 ARIMA order (p,d,q)

are used to fit the most appropriate model.

These models are accurate (for short term
demand forecasting) but highly cumbersome to
develop.

Back to main index exit back to module contents

 module 8: Production Planning

Past Data Current Data

Forecast Forecast
Generation Control

Managerial
Judgement
&
Experience

Modified
Forecast
Forecasting System
Back to main index exit back to module contents
 module 8: Production Planning

Moving Range Chart to Control

Forecasts

MR = | (Ft -Dt) - (Ft-1 - Dt-1) |

(Moving Range)

MR =  MR / (n – 1) ( There are n-1 moving

ranges for n period)
Upper Control Limit (UCL) = + 2.66 MR
Lower Control Limit ( LML) = - 2.66 MR
Back to main index exit back to module contents
 module 8: Production Planning

VARIABLE TO BE PLOTTED
30 = (Ft - Dt)
20
10
0
-10
-20

-30 Month

(Control Chart for

Example)

Back to main index exit back to module contents

To be cont.….