FORECASTING

What does Production planning and control deal with

PRODUCTION: that transformation of raw materials to finished goods. PLANNING: looks ahead, anticipates possible difficulties and decides in advance as to how the production, best, be carried out.

CONTROL: This phase makes sure that the programmed production is

constantly maintained.

Topics to be discussed in this chapter are

Demand Management Qualitative & Quantitative Forecasting Methods Simple & Weighted Moving Average Forecasts Simple Exponential Smoothing

Winters trend model

Before making an investment decision, many questions will arise like 1. 2. 3. 4. What should be the size or amount of capital required ? How large should be the size of work force ? What should be the capacity of plant? What should be the size of the order and safety stock?

Many factors influence the demand for a product. Some of them are: 1. General business and economic conditions.

2.
3. 4.

Competitive factors.
Market trends. The firms own plans for advertising, promotion, pricing, and product

changes.

Demand Management
Demand management is the process of recognizing and managing all demands for products. If material and capacity resources are to be planned effectively, all sources of demand must be identified. Demand management includes four major activities: 1. 2. Forecasting. Order processing.

3.
4.

Making delivery promises.

Interfacing between manufacturing planning and control and the marketplace

Demand Management
A company can : 1. Can take an active role to influence demand: I. Apply pressure on sales personnel II. Incentives to sales personnel or customers

2. Take a passive role and simply respond to demand I. II. Market may be fixed & static Powerless to change demand (heavy expense for advt.)

I.

Demand beyond control

Forecasting as defined by American Manufacturing Association is : An estimate of sales in physical units for a specified future period under proposed marketing plan or programme and under the assumed set of economic and other forces outside the organization for which the forecast is made .

Forecasting is Prelude to planning. Before making plans, an estimate must be made of what conditions exist over some future period.
In other words demand for a product must be known to the firm or company to reduce the delivery time to the customer. Firm must plan to provide the capacity and resources to meet that demand. Firms that make to order cannot begin making a product before a customer places an order but must have the resources of labor and equipment available to meet demand.

Principles Of Forecasting Forecasts have four major characteristics or principles. 1. Forecasts are usually wrong. Forecasts attempt to look into the unknown future and so errors are inevitable. 2. Every forecast should include an estimate of error. Since forecasts are expected to be wrong, the real question is, By how much? 3. Forecasts are more accurate for families or groups. The behavior of

individual items in a group is random even when the group has very stable
characteristics. For eg., the marks for individual students in a class are more difficult to forecast accurately than the class average.

Principles Of Forecasting

4. Forecasts are more accurate for nearer time periods. Near future holds less uncertainty than the far future. Most people are more confident in forecasting what they will be doing over the next week than a year from now

Forecasting period:
1. 2. 3. Short term: up to one year medium term: 1-3 years Long term: > 5 years

Forecasting Techniques: There are many forecasting methods, but usually classified into 3 categories: qualitative, extrinsic, and intrinsic.
Qualitative (Judgmental) techniques are projections based on judgment, intuition, and informed opinions. Estimating the demand the for a new product by 1. market survey 2. Data from salesperson 3. Based on demand of a similar product already in the market 4. Advise from a group of experts.

Quantitative methods (i) Extrinsic forecasting techniques are projections based on external (extrinsic) indicators which relate to the demand for a companys products. The theory is that the demand for a product group is directly proportional, or correlates, to activity in another field. Examples of correlation are: 1. Sales of bricks/cement are proportional to housing stats. 2.Sales of automobile tires are proportional to sale of automobiles. 3. Sales of appliances and disposable income.

Intrinsic forecasting techniques use historical data to forecast. These data are
usually recorded in the company and are readily available. Intrinsic forecasting techniques are based on the assumption that what happened in the past will happen in the future.

Components of Demand

Trend: An average or general tendency of a series of data points to move in a certain direction over time, represented by a line on a graph. The trend in the above case is a upward linear one. It is the long run historical component of the time series which indicates overall growth or decline of the business over time.

Seasonal variations: Patterns of change in demand within a year. These patterns tend to repeat themselves each year. The result of the weather, holiday seasons, or particular events that take place on a seasonal basis. Seasonality is usually thought of as occurring on a yearly basis, but it can also occur on a weekly or even daily basis.

Random variations: were factors influence the demand randomly.

Cyclical variation: The rise and fall of demand (a time series) over periods longer than one year. Over a span of several years, wavelike increase and decrease in the economy influence demand.

Time series forecasting models 1. Simple moving average 2. Weighted moving average 3. Simple Exponential smoothing 4. Winters Trend model

Simple Moving Average Formula

The simple moving average model assumes an average is a good estimator of future behavior The formula for the simple moving average is:

A t-1 + A t-2 + A t-3 +...+A t- n Ft = n

Ft = Forecast for the coming period N = Number of periods to be averaged A t-1 = Actual occurrence in the past period for up to n periods

15-24

Simple Moving Average Problem (1)

Moving average (MA) = (Sum of old demand for last n periods) (No. of periods used in the model)
Week 1 2 3 Demand 650 678 720

Question: What is the 3week moving average forecast for demand data shown in the table?

15-25

Simple Moving Average Problem (1)

MA t = MAt - 1
Week 1 2 3 4 5 6 Demand 650 678 720 785 859 920

D t - D t -n n

Question: What is the 6-week moving average forecast for demand?

Week 1 2 3 4 5 6 7 8 9 10 11 12

Demand 3-Week 6-Week 650 F4=(650+678+720)/3 678 =682.67 720 F7=(650+678+720 +785+859+920)/6 785 682.67 859 727.67 =768.67 920 788.00 850 854.67 768.67 758 876.33 802.00 892 842.67 815.33 920 833.33 844.00 789 856.67 866.50 844 867.00 854.83

Plotting the moving averages and comparing them shows how the lines smooth out to reveal the overall upward trend in this example

12
950 900 850 800 750 700 650 600 550 500

844

867.00

854.83

Demand

Demand 3-Week 6-Week

1 2 3 4 5 6 7 8 9 10 11 12 Week

Note how the 3-Week is smoother than the Demand, and 6-Week is even smoother

Example Problem 1. (a) Demand over the past three months has been 120, 135, and 114 units. Using a three-month moving average, calculate the forecast for the fourth month. Ans: 123

(b) If the actual demand for the fourth month turned out to be 129. Calculate the forecast for the fifth month. Ans: 126

Weighted Moving Average Formula

While the moving average formula implies an equal weight being placed on each value that is being averaged, the weighted moving average permits an unequal weighting on prior time periods

The formula for the moving average is:

Ft = w 1 A t -1 + w 2 A t - 2 + w 3 A t -3 + ...+ w n A t - n
wt = weight given to time period t occurrence (weights must add to one)

w
i=1

=1

Weighted Moving Average Problem (1) Data

Question: Given the weekly demand and weights, what is the forecast for the 4th period or Week 4?
Week 1 2 3 4 Demand 650 678 720

Weights: (t-1) .5 (t-2) .3 (t-3) .2

Note that the weights place more emphasis on the most recent data, that is time period t-1

Weighted Moving Average Problem (1) Solution

Week 1 2 3 4

Demand Forecast 650 678 720 693.4

F4 = 0.5(720)+0.3(678)+0.2(650)=693.4

Weighted Moving Average Problem (2) Data

Question: Given the weekly demand information and weights, what is the weighted moving average forecast of the 5th period or week?

Week 1 2 3 4

Demand 820 775 680 655

Weights: (t-1) .7 (t-2) .2 (t-3) .1

Weighted Moving Average Problem (2) Solution

Week 1 2 3 4 5

Demand Forecast 820 775 680 655 672

F5 = (0.1)(775)+(0.2)(680)+(0.7)(655)= 672

EXPONENTIAL SMOOTHING FORECAST

Ft = Ft-1 + a(Dt-1 - Ft-1)

Where : Ft Forcast value for thecoming time period ' t' Ft - 1 Forecast value for themost recent past timeperiod At - 1 Actual demand for themost recent past timeperiod a Alpha smoothingconstant

Premise: The most recent observations might have the highest predictive value Therefore, we should give more weight to the more recent time periods when forecasting

Exponential Smoothing Average

Ft = Ft-1 + a(Dt - Ft-1)

Where : Ft Forcast value for thecoming time period ' t' Ft - 1 Forecast value for themost recent past timeperiod Dt Actual demand for theCurrent time period a Alpha smoothingconstant
Premise: The most recent observations might have the highest predictive value Therefore, we should give more weight to the more recent time periods when forecasting

SIMPLE EXPONENTIAL SMOOTHING

A special type of weighted moving average

Include all past observations

Use a unique set of weights that weight recent observations much more heavily than very old observations:

weight
Decreasing weights given to older observations

0 a 1
a a (1 a ) a (1 a ) 2 a (1 a ) 3

Today

SIMPLE ES: THE MODEL

Ft aYt 1 a (1 a )Yt 2 a (1 a ) 2 Yt 3 Ft aYt 1 (1 a )aYt 2 a (1 a )Yt 3

Ft aYt 1 (1 a ) Ft 1
New forecast = weighted sum of last period actual value and last period forecast
a:

Smoothing constant Forecast for period t Last period forecast Last period actual value

Ft : Ft-1: Yt-1:

SIMPLE EXPONENTIAL SMOOTHING

Properties of Simple Exponential Smoothing

Widely used and successful model

Requires very little data

Formulating an exponential model is relatively easy Little computation is required to use the model

Larger a, more responsive forecast; Smaller a, smoother forecast

Computer storage requirements are small because of the limited use of historical data

Suitable for relatively stable time series

38

EXPONENTIAL SMOOTHING PROBLEM (1) DATA

Week 1 2 3 4 5 6 7 8 9 10

Demand 820 775 680 655 750 802 798 689 775

Question: Given the weekly demand data, what are the exponential smoothing forecasts for periods 2-10 using a=0.10 and a=0.60? Assume F1=D1

Answer: The respective alphas columns denote the forecast values. Note that you can only forecast one time period into the future.

Week 1 2 3 4 5 6 7 8 9 10

Demand 820 775 680 655 750 802 798 689 775

0.1 820.00 820.00 815.50 801.95 787.26 783.53 785.38 786.64 776.88 776.69

0.6 820.00 820.00 793.00 725.20 683.08 723.23 770.49 787.00 728.20 756.28

EXPONENTIAL SMOOTHING PROBLEM (1) PLOTTING

Note how that the smaller alpha results in a smoother line in this example

850 800 750 700 650 600 550 500 1 2 3 4 5 6 7 8 9 10 Week

Demand

Demand
0.1

0.6

EXPONENTIAL SMOOTHING PROBLEM (2) DATA

Week Demand Question: What are 1 820 the exponential 2 775 smoothing forecasts 3 680 for periods 2-5 using 4 655 a =0.5? 5

Assume F1=D1

EXPONENTIAL SMOOTHING PROBLEM (2) SOLUTION

F1=820+(0.5)(820-820)=820

F3=820+(0.5)(775-820)=797.75

Week 1 2 3 4 5

Demand 820 775 680 655

0.5 820.00 820.00 797.50 738.75 696.88

WINTERS TREND MODEL

MONTH January February March April May June

Demand 89 57 144 221 177 280

Month July August September October November December

Demand 223 286 212 275 188 312

Trend implies a pattern of change over time.

PATTERN-BASED FORECASTING SEASONAL

Once data turn out to be seasonal, deseasonalize the data. Make forecast based on the deseasonalized data Reseasonalize the forecast

Good forecast should mimic reality. Therefore, it is needed to give seasonality back.

PATTERN-BASED FORECASTING SEASONAL

Actual data Deseasonalize

Deseasonalized data

Forecast

Reseasonalize

PATTERN-BASED FORECASTING SEASONAL

Deseasonalization

Deseasonalized data = Actual / SI

Reseasonalization

Reseasonalized forecast = deseasonalized forecast * SI

59

SEASONAL INDEX

Whats an index?
Ratio SI

= ratio between actual and average demand for quarter demand is 1.20

Suppose
SI
Whats

that mean? Use it to forecast demand for next fall

So,

where did the 1.20 come from?!

60

CALCULATING SEASONAL INDICES

Quick method of calculating SI

For

each year, calculate average demand Divide each demand by its yearly average
This

creates a ratio and hence a raw index For each quarter, there will be as many raw indices as there are years
Average

the raw indices for each of the quarters The result will be four values, one SI per quarter

61

CLASSICAL DECOMPOSITION
Start by calculating seasonal indices Then, deseasonalize the demand

Divide

actual demand values by their SI values

y = y / SI
Results

in transformed data (new time series) Seasonal effect removed

Forecast Reseasonalize with SI

62