2. 3-2 Forecasting
FORECAST:
A statement about the future value of a variable of interest
such as demand.
Forecasts affect decisions and activities throughout an
organization
Accounting, finance
Human resources
Marketing
MIS
Operations
Product / service design
Supply chain
3. 3-3 Forecasting
It is a technique that uses
historical data as inputs to
make informed estimates
that are predictive in
determining the direction of
future trends.
4. 3-4 Forecasting
Uses of Forecasts
Accounting Cost/profit estimates
Finance Cash flow and funding
Human Resources Hiring/recruiting/training
Marketing Pricing, promotion, strategy
MIS IT/IS systems, services
Operations Schedules, MRP, workloads
Product/service design New products and services
5. 3-5 Forecasting
Assumes causal system
past ==> future
Forecasts rarely perfect because of
randomness
Forecasts more accurate for
groups vs. individuals
Forecast accuracy decreases
as time horizon increases
I see that you will
get an A this semester.
6. 3-6 Forecasting
Supply chain forecasts
within the supply chain context there are
three types of forecasting, which are:
Demand forecasting: This is the
investigation of the companies demand for
an item, to include current and projected
demand by industry and product end use.
7. 3-7 Forecasting
Supply forecasting: Is a
collection of data about the
current producers and
suppliers, as well as
technological and political
trends that might affect supply.
8. 3-8 Forecasting
Price forecast: This is based
on information gathered and
analysed about demand and
supply. Provides a prediction of
short- and long-term prices and
the underlying reasons for
those trends.
9. 3-9 Forecasting
Importance of forecasts in supply chain
1. Increasing customer satisfaction
In order to keep your customers satisfied
you need to provide them with the product
they want when they want it. This
advantage of forecasting in business will
help predict product demand so that
enough product is available to fulfil
customer orders with short lead times, on-
time.
10. 3-10 Forecasting
The importance of Demand
Forecasting is much higher
in: Made-to-Stock (MTO),
Assemble-to-Order (ATO)
or JIT Supply Business.
11. 3-11 Forecasting
2. Reducing inventory stockouts
Businesses need realise the importance of
demand forecasting, even if you are
working in JIT System or with long lead
time suppliers like India or China. If you
are buying from long lead time suppliers
then you need to send a demand forecast
so that suppliers can arrange raw materials
in anticipation of actual customer orders.
12. 3-12 Forecasting
In the case of JIT Systems, demand
forecasting helps you to time your
purchases to correspond to when sales
need to be fulfilled.
The less time inventory spends in the
warehouse, the less money you’re
paying to let it just sit there waiting to
be sold.
13. 3-13 Forecasting
3. Scheduling production more effectively
Forecasting is often compared to driving a car while
looking in the rear-view mirror.
The past gives a few clues about the future, but not
enough to stop you from driving off a cliff, but in my
opinion this is the best view you’ve got!
If you look into the 5 Levels of Planning Hierarches
most business should need robust SIOP (sales
inventory operations planning) and Master
Scheduling to schedule production more effectively.
14. 3-14 Forecasting
4. Lowering safety stock requirement
A good demand forecasting process will have a direct impact
in the planning of inventory levels,
Link:
Developing production requests to manufacturing
operations
Planning for new product launches
Planning for promotional activity
Planning for seasonal variations in demand
If a business is using forecasting to plan any of the above
scenarios then you don’t need to carry high safety stocks to
manage those events.
15. 3-15 Forecasting
5. Reducing product obsolescence costs
By identifying, repurposing or removing
obsolete inventory the volume of
inventory on hand will decrease.
With this, both direct and indirect costs of
keeping the obsolete inventory will be
reduced. This closely links to reduced
order sizes as a smaller volume of the
inventory will be in stock and demand
forecast accuracy.
16. 3-16 Forecasting
Having a standardised
reliable way of forecasting
demand will mean that
excess stock is not ordered
and this will reduce the
chance of obsolete stock.
17. 3-17 Forecasting
6. Managing shipping better
Nothing annoys me more than
doing everything you can to
make or buy a product so that
it’s available to ship on-time
yet the warehouse guys won’t
ship, as they don’t have enough
people.
18. 3-18 Forecasting
For that reason the logistics guys are now
part of the SIOP process and they have to
tell how many people they need in the next
several months to ensure we have enough
capacity to ship material on time.
This is one of the classic examples to
demonstrate the importance of demand
forecasting.
19. 3-19 Forecasting
7. Improving pricing and promotion management
In some businesses, multiple promotions running
concurrently may result in the cannibalisation of both
promoted and non-promoted SKUs. (stock keeping
unit)
Integrating distributor-level promotions and related
forecasts will allow you to improve the flow of goods
and achieve better results in terms of availability and
stock fill rates.
Similarly, improving the ability to forecast the impact
price changes will have on both revenue and gross
margin dollars, when timed well!
20. 3-20 Forecasting
Forecasting should not be a knee-
jerk reaction of complaining to the
supplier or shouting at the VP, there
are plenty of more productive
methods including gathering data,
getting it into shape to analyse and
creating a base demand forecast.
22. 3-22 Forecasting
Steps in the Forecasting Process
Step 1 Determine purpose of forecast
Step 2 Establish a time horizon
Step 3 Select a forecasting technique
Step 4 Gather and analyze data
Step 5 Prepare the forecast
Step 6 Monitor the forecast
“The forecast”
23. 3-23 Forecasting
Types of Forecasts
Judgmental - uses subjective (personal
feelings, tastes or opinions) inputs
Time series - uses historical data
assuming the future will be like the past
Time series models look at past patterns
of data and attempt to
predict the future based upon the
underlying patterns contained
24. 3-24 Forecasting
Associative models - uses explanatory
variables to predict the future.
Associative models (often called causal
models) assume that the variable being
forecasted is related to other variables in
the environment. They try to project based
upon those associations.
25. 3-25 Forecasting
Judgmental Forecasts
Executive opinions
Sales force opinions
Consumer surveys
Outside opinion
Delphi method
Opinions of managers and staff
Achieves a consensus forecast
26. 3-26 Forecasting
Time Series Forecasts
Trend - long-term movement in data. Data exhibit a steady
growth or decline over time.
Seasonality - short-term regular variations in data
Cycle – wavelike variations of more than one year’s
duration. Data exhibit upward and downward swings in
over a very long time frame.
Irregular variations - caused by unusual circumstances
Random variations - caused by chance. Erratic and
unpredictable variation in the data over time with no
discernable pattern.
29. 3-29 Forecasting
Naive Forecasts
Uh, give me a minute....
We sold 250 wheels last
week.... Now, next week
we should sell....
The forecast for any period equals
the previous period’s actual value.
30. 3-30 Forecasting
Simple to use
Virtually no cost
Quick and easy to prepare
Data analysis is nonexistent
Easily understandable
Cannot provide high accuracy
Can be a standard for accuracy
Naïve Forecasts
32. 3-32 Forecasting
Naïve forecasting
Year Actual Demand (At) Forecast (Ft) Notes
1 310 --- There was no prior demand data
on which to base a forecast for
period 1
2 365 310 From this point forward, these
forecasts were made on a year-
by-year basis.
3 395 365
4 415 293
5 450 415
6 465 450
7 465
33. 3-33 Forecasting
Techniques for Averaging
Mean (Simple Average)
Method
Moving average
Weighted moving average
Exponential smoothing
34. 3-34 Forecasting
MEAN
(SIMPLE AVERAGE) METHOD
Mean (simple average)
method: The forecast for next
period (period t+1) will be
equal to the average of all
past historical demands
35. 3-35 Forecasting
Year Actual Demand (At) Forecast (Ft) Notes
1 310 300 This forecast was a
guess at the
beginning.
2 365 310.000 From this point forward, these
forecasts were made on a year
-by-year basis using a simple
average approach
3 395 337.500
4 415 356.667
5 450 371.250
6 465 387.000
7 400.000
37. 3-37 Forecasting
Moving Averages
Moving average – A technique that averages a number of
recent actual values, updated as new values become
available.
MAn =
n
Ai
i = 1
n
38. 3-38 Forecasting
Simple moving average method: The forecast
for next period (period t+1) will be equal to the
average of a specified number of the most
recent observations, with each observation
receiving the same emphasis (weight).
In this illustration we assume that a 2-year
simple moving average is being used.
We will also assume that, in the absence of data
at startup, we made a guess for the year 1
forecast (300).
39. 3-39 Forecasting
Then, after year 1 elapsed, we
made a forecast for year 2 using a
naïve method (310). Beyond that
point we had sufficient data to let
our 2-year simple moving average
forecasts unfold throughout the
years.
40. 3-40 Forecasting
Year Actual Demand (At) Forecast (Ft) Notes
1 310 300 This forecast was a guess at
the beginning.
2 365 310 This forecast was made using
a naïve approach.
3 395 337.500 From this point forward,
these forecasts were made on
a year-by-year basis using a
2-yr moving average
approach.
4 415 380.000
5 450 405.000
6 465 432.500
7 457.500
41. 3-41 Forecasting
ANOTHER SIMPLE MOVING AVERAGE
ILLUSTRATION
In this illustration we assume that a 3-year
simple moving average is being used. We will
also assume that, in the absence of data at
startup, we made a guess for the year 1 forecast
(300).
Then, after year 1 elapsed, we used a naïve
method to make a forecast for year 2 (310) and
year 3 (365). Beyond that point we had
sufficient data to let our 3-year simple moving
average forecasts unfold throughout the years.
42. 3-42 Forecasting
Year Actual Demand (At) Forecast (Ft) Notes
1 310 300 This forecast was a guess at the
beginning.
2 365 310 This forecast was made using a
naïve approach.
3 395 365 This forecast was made using a
naïve approach.
4 415 356.667 From this point forward, these
forecasts were made on a year-by-
year basis using a 3-yr moving
average approach
5 450 391.667
6 465 433.333
43. 3-43 Forecasting
WEIGHTED MOVING AVERAGE METHOD
Weighted moving average
– More recent values in a
series are given more
weight in computing the
forecast.
44. 3-44 Forecasting
Weighted moving average method: The forecast
for next period (period t+1) will be equal to a
weighted average of a specified number of the
most recent observations.
In this illustration we assume that a 3-year
weighted moving average is being used. We
will also assume that, in the absence of data at
startup, we made a guess for the year 1 forecast
(300).
45. 3-45 Forecasting
Then, after year 1 elapsed, we used a
naïve method to make a forecast for year
2 (310) and year 3 (365). Beyond that
point we had sufficient data to let our
3-year weighted moving average forecasts
unfold throughout the years. The weights
that were to be used are as follows: Most
recent year, .5; year prior to that, .3; year
prior to that, .2
46. 3-46 Forecasting
EXAMPLE 1
Year Actual
Demand (At)
Forecast (Ft) Notes
1 310 300 This forecast was a guess at the
beginning.
2 365 310 This forecast was made using a
naïve approach.
3 395 365 This forecast was made using a
naïve approach.
4 415 369 From this point forward, these
forecasts were made on a year-by-
year basis using a 3-yr wtd.
moving avg. approach.
5 450 399.000
6 465 428.500
7 450.500
48. 3-48 Forecasting
EXAMPLE 2
The manager of a restaurant wants to make decision
on inventory and overall cost. He wants to forecast
demand for some of the items based on weighted
moving average method. For the past three months
he experienced a demand for pizzas as follows:
Month Demand
October 400
November 480
December 550
Find the demand for the month of January by assuming
suitable weights to demand data
51. 3-51 Forecasting
Exponential Smoothing
Exponential smoothing method: The new forecast
for next period (period t) will be calculated as
follows:
New forecast = Last period’s forecast + α(Last
period’s actual demand – Last period’s forecast)
52. 3-52 Forecasting
Ft = Ft-1 + α(At-1 – Ft-1)
Sinplified
Ft = αAt-1 + (1-α)Ft-1
Where α is a smoothing
coefficient whose value is
between 0 and 1.
53. 3-53 Forecasting
To make a forecast for next period, we would use the user
friendly alternate equation 1:
Ft = αAt-1 + (1-α)Ft-1 (equation 1)
When we made the forecast for the current period (Ft-1), it
was made in the following fashion:
Ft-1 = αAt-2 + (1-α)Ft-2 (equation 2)
If we substitute equation 2 into equation 1 we get the
following:
Ft = αAt-1 + (1-α)[αAt-2 + (1-α)Ft-2]
Which can be cleaned up to the following:
Ft = αAt-1 + α(1-α)At-2 + (1-α)2Ft-2 (equation 3)
54. 3-54 Forecasting
We could continue to play that game by recognizing
that Ft-2 = αAt-3 + (1-α)Ft-3 (equation 4)
If we substitute equation 4 into equation 3 we get the
following:
Ft = αAt-1 + α(1-α)At-2 + (1-α)2[αAt-3 + (1-α)Ft-3]
55. 3-55 Forecasting
Which can be cleaned up to the following:
Ft = αAt-1 + α(1-α)At-2 + α(1-α)2At-3 + (1-α)3Ft-3
If you keep playing that game, you should recognize
that
Ft = αAt-1 + α(1-α)At-2 + α(1-α)2At-3 + α(1-α)3At-4 + α
(1-α)4At-5 + α (1-α)5At-6 ……….
56. 3-56 Forecasting
EXAMPLE 1
In this illustration we assume that, in the absence of
data at startup, we made a guess for the year 1
forecast (300).
Then, for each subsequent year (beginning with year
2) we made a forecast using the exponential
smoothing model.
After the forecast was made, we waited to see what
demand unfolded during the year.
We then made a forecast for the subsequent year, and
so on right through to the forecast for year 7.
57. 3-57 Forecasting
This set of forecasts was made using an
value of 0.1
Year Actual Demand
(A)
Forecast ( F ) Notes
1 310 300 This was a guess, since there was no prior
demand data.
2 365 301 From this point forward, these forecasts were
made on a year-by-year basis using exponential
smoothing with α=.1
3 395 307.4
4 415 316.16
5 450 326.044
6 465 338.4396
7 351.4396
59. 3-59 Forecasting
EXAMPLE 2
This set of forecasts was made using an α value of 0.2
Year Actual
Demand
( A)
Forecast
( F)
NOTES
1 310 300 This was a guess, since there was no prior demand data.
2 365 302 From this point forward, these forecasts were made on a
year-by-year basis using exponential smoothing with
α= 0.2
3 395 314.6
4 415 330.68
5 450 347.544
6 465 368.0352
7 387.42816
61. 3-61 Forecasting
EXAMPLE 3
This set of forecasts was made using an α value of 0.4
Year Actual Demand
(At)
Forecast
(Ft)
Notes
1 310 300 This was a guess, since there was no prior demand
data.
2 365 304 From this point forward, these forecasts were made
on a year-by-year basis using exponential smoothing
with α =0.4
3 395 328.4
4 415 355.04
5 450 379.024
6 465 407.4144
7 430.44864
63. 3-63 Forecasting
Linear Trend Equation
Ft = Forecast for period t (demand)
t = Specified number of time periods
a = Value of Ft at t = 0
b = Slope of the line
Ft = a + bt
0 1 2 3 4 5 t
Ft
65. 3-65 Forecasting
Linear Trend Equation Example
t y
Week t2
Sales ty
1 1 150 150
2 4 157 314
3 9 162 486
4 16 166 664
5 25 177 885
t = 15 t2
= 55 y = 812 ty = 2499
(t)2
= 225
66. 3-66 Forecasting
Linear Trend Calculation
y = 143.5 + 6.3t
a =
812 - 6.3(15)
5
=
b =
5 (2499) - 15(812)
5(55) - 225
=
12495-12180
275-225
= 6.3
143.5
67. 3-67 Forecasting
Forecast Accuracy
Error - difference between actual value and predicted
value
Mean Absolute Deviation (MAD)
Average absolute error
Mean Squared Error (MSE)
Average of squared error
Mean Absolute Percent Error (MAPE)
Average absolute percent error
68. 3-68 Forecasting
Mean absolute deviation (MAD) review
The mean absolute deviation
of a dataset is the average
distance between each data
point and the mean. It gives
us an idea about the
variability in a dataset.
69. 3-69 Forecasting
how to calculate the mean absolute
deviation
Step 1: Calculate the mean.
Step 2: Calculate how far away each data
point is from the mean using positive
distances. These are called absolute
deviations.
Step 3: Add those deviations together.
Step 4: Divide the sum by the number of
data points.
70. 3-70 Forecasting
MAD, MSE, and MAPE
MAD =
Actual forecast
n
MSE =
Actual forecast)
-1
2
n
(
MAPE =
Actual forecas
t
n
/ Actual*100)
(
71. 3-71 Forecasting
Controlling the Forecast
Control chart
A visual tool for monitoring forecast errors
Used to detect non-randomness in errors
Forecasting errors are in control if
All errors are within the control limits
No patterns, such as trends or cycles, are
present
72. 3-72 Forecasting
Sources of Forecast errors
Model may be inadequate
Irregular variations
Incorrect use of forecasting technique
73. 3-73 Forecasting
Tracking Signal
Tracking signal =
(Actual-forecast)
MAD
•Tracking signal
–Ratio of cumulative error to MAD
Bias – Persistent tendency for forecasts to be
Greater or less than actual values.
74. 3-74 Forecasting
Choosing a Forecasting Technique
No single technique works in every situation
Two most important factors
Cost
Accuracy
Other factors include the availability of:
Historical data
Computers
Time needed to gather and analyze the data
Forecast horizon