Demand Forecasting

 What is Forecasting?
 A forecast is an estimate of what is likely to happen in
the future.
 Forecasts are concerned with determining what the
future will look like; planning is concerned with what it
should look like.
 Forecasting provides a basis for coordinating activities
in various parts of the company.
 Forecasts are an important input to both long-term,
strategic decision-making, as well as for short-term
planning for day-to-day operations.

1
 Demand Forecasting
 Importance of Forecasting
Forecasting is important for all of the functional areas of
business:

Finance uses long-term forecasts for capital planning

and short-term forecasts for budgeting.
Marketing produces sales forecasts for market
planning and market strategy.
Operations develops and uses forecasts for
scheduling, inventory management, and long-term
capacity planning.
Human Resource Management uses forecasts to
estimate the need for employees.
 Demand Forecasting

 Types of Forecasts

There are three major types of forecasts:

1. Demand Forecasts these are estimates of demand for a
company’s goods or services.

2. Technological Forecasts These are forecasts concerned

with the rate of change in technology and the impact on
a company’s revenues and/or costs.

3. Economic Forecasts predict inflation rates, employment

rates, money supply, housing starts, and other measures
of the performance of an economy.

3
 Demand Forecasting

 Features of Forecasts
All forecasting techniques have the same features:

1. Forecasting techniques assume that the same basic or

original system that existed in the past will exist in the
future.

2. Forecasts are rarely perfect.

3. Forecast accuracy decreases as the time horizon

increases.

4. Forecasts for groups of items are more accurate than

forecasts for individual items.

4
 Demand Forecasting

 Elements of a Good Forecast

A properly prepared forecast should meet the following
requirements:

1. The forecast should be accurate.

2. The forecast should be timely.
3. The forecast should be reliable.
4. The forecasting technique should be simple to
understand and use.
5. The forecast should be expressed in meaningful units.
6. The forecast should be in writing.

5
 Demand Forecasting

 Steps in the Forecasting Process

There are seven basic steps in the forecasting process:
1. Determine the purpose of the forecast.

2. Select the items to be forecast.

3. Establish a time horizon.

4. Select the forecasting technique.

5. Gather and analyze relevant data.

6. Prepare the forecast.

7. Monitor the results.

6
 Demand Forecasting
 Forecasting Approaches
There are two major approaches to forecasting: qualitative
(judgmental) and quantitative methods.

Further, quantitative methods can be divided into ones that use

historical data (time series models) or ones that develop
relationships between variables (associative models).

Forecasts Based on Judgment Judgmental forecasts rely on

analysis of subjective inputs from a variety of sources
including customer surveys, sales staff, managers, and
panels of experts.

Forecasts Based on Time Series Data Some forecasting

techniques use historical, or time series data, with the
assumption that the future will be like the past.

7
 Demand Forecasting

 Forecasts Based on Judgment

 Executive Opinion A forecasting method in which the opinions
and experience of one or more managers are used to produce a
forecast.
 Sales Force Opinion Forecasts compiled from estimates of
demand made by members of a company’s sales force.
 Customer Surveys A forecasting method that seeks input from
customers regarding future purchasing plans for existing
products or services.
 Market Research This method tests hypothesis about new
products or services or new markets for existing products or
services.
 Delphi Method A forecasting technique using a group process
that allows experts to make forecasts.

8
 Demand Forecasting

 Forecasts Based on Time Series Data

 A time series is a sequential series of observations taken at
regular intervals over a period of time.
 The data may be demand (units or dollars), output (units),
profits (dollars), or CPI (indices), among others.
 Analysis of time series data seeks to identify the underlying
behavior of the series. The underlying behavior is made up
of patterns such as:
 Trend
 Cycles
 Seasonality
 Random variation

9
 Demand Forecasting
Classification of Forecasting Methods
F o reca stin g

Q u a n tita tiv e Q u a lita tiv e

T im e S eries A ssociative E xecutive

M odels M odels O pinions

S alesforce
N aive T ech n iq u es T ech n iq u es T ech n iq u es S im p le M u ltip le
F orecast for A veragin g for T ren d for S eason ality L in ear R egression L in ear R egression O pinions

C onsum er
S im p le Trend T r e n d a n d S e a so n a l
M o vin g A ve r a g e E x p o n e n tia l S m o o th in g E x p o n e n tia l S m o o th in g S urveys
W e ig h te d
M o vin g A ve r a g e
Trend
P r o je c tio n
Trend
P r o je c tio n
M ark et
R esearch
S im p le
E x p o n e n tia l S m o o th in g
M arket
S u rveys

M arket
T ests

D elp hi
M ethod

10
 Demand Forecasting

 Overview of Time Series Forecasting

 A time series consists of a sequential set of data of a
variable, such as demand.
 There are four possible components of demand:
 Trend . A gradual upward or downward movement of the data over
time.
 Cycles. Wavelike variations in the data that occur every several years.
 Seasonality. Short-term, fairly regular variations that are generally
related to weather factors or to human-made factors such as holidays.
 Random Variations. “Blips “ in the data caused by chance and
unusual situations. They follow no discernable pattern, so they cannot
be predicted.

11
 Demand Forecasting

Figure 1: Product Demand Charted Over 4 Years with a Growth Trend and Seasonality

Seasonal peaks Trend

component

Average demand
over four years

Random variation

Year Year Year Year

1 2 3 4

12
 Demand Forecasting

 Naive Forecasts
 A forecast that assumes that demand in the next period
will be equal to demand in the most recent period.
 Can handle the following components of demand:
 Random variation. The last data point becomes the forecast for the
next period.
 Seasonal variation. The forecast for “this season” is equal to the
value of the series “last season”.
 Trend. The forecast is equal to the last value of the data series,
plus or minus the difference between the last two values.

13
 Demand Forecasting

 Techniques for Averaging

 These are techniques that are useful for data that has only
random variation.
 These techniques smooth fluctuations in a time series.
 Forecasts that are based on an average are more “stable”
than the original data.
 There are three popular averaging techniques:
 Simple moving average
 Weighted moving average
 Simple exponential smoothing

14
 Demand Forecasting
 Moving Average
 A technique that uses a number of historical data values to generate a
forecast.
 Involves finding a series of successive averages by dropping the first
data value in the series and adding the last data value.
 Useful for data without trend, seasonality, or cycles.

Weekly Patient Arrivals at a Medical Clinic

475
Patient Arrivals

450

425

400

375

350
1 4 7 10 13 16 19 22 25 28
Week
 Demand Forecasting
 Simple Moving Average
 A key decision involves selecting the number of periods that will be included
in the average.
 The larger the number of periods, the greater the smoothing; the smaller the
number of periods, the quicker the forecast reacts to changes in the data.

Example of Three- and Five-Period Moving Average

3-Period 5-Period
100
MA MA
Period Demand Forecast Forecast 90
1 53
Demand

2 62 80
3 84
4 78 66.3 70
5 95 74.7
6 75 85.7 74.4 60
7 66 82.7 78.8
8 82 78.7 79.6 50
9 71 74.3 79.2 1 2 3 4 5 6 7 8 9 10
10 83 73.0 77.8
78.7 75.4 Period
Demand 3-Period MA 5-Period MA

16
 Demand Forecasting
Example 1 – Simple Moving Average Illustration

Market Mixer, Inc. sells can openers. Monthly sales for an eight-month period were as
follows:
Month Sales Month Sales
1 450 5 460
2 425 6 455
3 445 7 430
4 435 8 420
Forecast next month’s sales using a 3-month moving average.
Solution:
Period Sales Moving Average Forecast Comments:
1 450 1. Any forecasts beyond Period 9 will
2 425 have the same value as the Period 9
forecast; i.e., 435.
3 445
2. As a new actual value becomes
4 435 (450 + 425 + 445) / 3 = 440 available, the forecast will be updated
5 460 (425 + 445 + 435) / 3 = 435 by adding the newest value and
6 455 (445 + 435 + 460) / 3 = 447 dropping the oldest one.
7 430 (435 + 460 + 455) / 3 = 450 3. SMA gives equal weight to all values
in the average. Hence, the oldest
8 420 (460 + 455 + 430) /3 = 448 value has the same weight, or
9 (455 + 430 + 420) / 3 = 435 importance, as the newest.

17
 Demand Forecasting

Weighted Moving Average

 A model that applies different “weights” to each value in the moving
average calculation.
 Two key decisions:
 The number of periods that will be included in the average. The larger
the number of periods, the greater the smoothing; the smaller the
number of periods, the quicker the forecast reacts to changes in the
data.
 The weight that will be applied to each period. The higher the weight
applied to more recent data, the quicker the model reacts to changes;
the lower the weight that is applied to the more recent data, the greater
is the smoothing process.
 Demand Forecasting
Example 2 – Weighted Moving Average Illustration
(Let us continue with the same problem as we had in Example 1.) Market Mixer, Inc.
sells can openers. Monthly sales for an eight-month period were as follows:
Month Sales Month Sales
1 450 5 460
2 425 6 455
3 445 7 430
4 435 8 420
Forecast next month’s sales using a 3-month weighted moving average, where the
weight for the most recent data value is 0.60; the next most recent, 0.30; and the earliest,
0.10.
Solution:
Period Sales Weighted Moving Average Forecast Comments:
1 450 1. Any forecasts beyond
2 425 Period 9 will have the same
value as the Period 9
3 445 forecast, i.e., 427.
4 435 (450*.10) + (425*.30) + (445*.60) = 440 3. WMA gives greater weight
5 460 (425*.10) + (445*.30) + (435*.60) = 437 to more recent values in the
6 455 (445*.10) + (435*.30) + (460*.60) = 451 moving average and is
more responsive to recent
7 430 (435*.10) + (460*.30) + (445*.60) = 455 changes in the data.
8 420 (460*.10) + (455*.30) + (430*.60) = 427
441
9 (445*.10) + (430*.30) + (420*.60) =
19
 Demand Forecasting

Simple Exponential Smoothing

 This is a variation of the weighted moving average model.
 Weights are determined by an exponential function which
declines as the data gets older.

 The formula: Ft+1 = At + (1 – )Ft

Where Ft+1 = forecast for next period

 = smoothing constant (0 <  < 1)
At = current period’s actual demand
Ft = current period’s forecast

20
 Demand Forecasting
Example 3 – Simple Exponential Smoothing Illustration
(Let us continue with the same problem as we had in Example 1.) Market Mixer, Inc.
sells can openers. Monthly sales for an eight-month period were as follows:
Month Sales Month Sales
1 450 5 460
2 425 6 455
3 445 7 430
4 435 8 420
Forecast next month’s sales using exponential smoothing with alpha () = 0.30 and the
first (starting) forecast = 450.
Solution:
Period Sales Exponential Smoothing Forecast
1 450 450
Comments:
2 425 (.30*450) + (1 - .30)*450 = 450
1. Any forecasts beyond Period 9
3 445 (.30*425) + (1 - .30)*450 = 443 will have the same value as the
4 435 (.30*445) + (1 - .30)*443 = 443 Period 9 forecast, i.e., 436.
5 460 (.30*435) + (1 - .30)*443 = 441 3. The higher the value of , the
6 455 (.30*460) + (1 - .30)*441 = 447 quicker the reaction to changes
in the data and the less the
7 430 (.30*455) + (1 - .30)*447 = 449 smoothing.
8 420 (.30*430) + (1 - .30)*449 = 443
9 (.30*420) + (1 - .30)*443 = 436