10/1/2024

Chapter 5. Basic Forecasting Methods

Nguyen VP Nguyen, Ph.D.

Department of Industrial & Systems Engineering, HCMUT
Email: [email protected]

Page 79
(P.34 E9)

1
 10/1/2024

Naïve Forecasts
• Uses a single previous value of a time series as the basis of
a forecast.
• Virtually no cost
• Data analysis is nonexistent
• Easily understandable
• Cannot provide high accuracy
 If it were true, future will always be the same as the past

Some notation:
 Forecast at time t is 𝑌 𝑡
 Actual observation at time t is Y(t)
 Today is temperature is 98 F, Y(Today) = 98
 𝑌 Tomorrow = 98
 𝑌 Day after) = 98

Last Period Demand (Naïve Model)

• Stable time series data
 The forecast for the next period is simply the actual demand
observed in the current period.
Yˆt 1  Yt
where 𝑌t+1 = forecast made at time t for time/period t+1
𝑌 = actual demand in the period t
 This model is particularly useful when demand is stable, and
there is no trend or seasonality. Its forecasts can be very
inaccurate for more complex, non-stationary time series.
 It’s also helpful as a benchmark to evaluate the performance
of more complex forecasting models.
4

2
 10/1/2024

Naïve Forecasts

• Seasonal variations
 Forecast is the same as the last actual observation when
we were in the same point in the cycle, where a cycle lasts
n periods. ˆYt 1  Yt  n
• Data with trends
 There is constant trend, the change from (t-2) to (t-1) will
be exactly as the change from (t-1) to (t)

Yˆt 1  Yt  (Yt  Yt 1 )

The naïve drift method

• The method incorporates the overall trend (drift) in the

data series from the first observation to the last and
extrapolates the trend observed in the historical data.
• not be suitable when the time
series has seasonality,
 Y Y  cyclical patterns, the trend is
Y t  h  Yt   t 1  h nonlinear.
 t 1  • the trend between the first
and the last observed value
where: is representative of the
overall trend in the series,
Y1 is the first observed value
which might not include
Yt is the last observed value series with structural breaks.
t is the total number of observations
h is the number of periods ahead you are forecasting
6

3
 10/1/2024

The naïve drift method

• This method is used for a quick, interpretable, and

trend-adjusted forecast without developing a more
complex model.
• Example: Alphabet Inc. (GOOG), Historical Prices,
Close* (Close price adjusted for splits)

Modified Naive Model

• Forecast value is equal to the previous observed

value plus a proportion of the most recently observed
rate of change in the variable.
• Use (Yt-1-Yt-2) to consider the direction from which we
arrived at the most recent observation.

Yt  Yt 1  p Yt 1  Yt  2 
where
Y1 is the first observed value.
p is the proportion of the change between
periods t-2 and t-1 that we choose to include in
the forecast
9

4
 10/1/2024

Forecast Accuracy of Naïve Model vs. Modified Naive Model

• Example 1: The quarterly sales of saws from 2000 to

2006 for the Acme Tool Company.
Naïve Modified Naïve
p 0.6

MAD 152.308 MAD 151.852

MSE 39907.692 MSE 29074.074
RMSE 199.769 RMSE 170.511
MAPE 0.357 MAPE 0.368

MPE -0.005 MPE -0.072

ME 14.615 ME 7.407
10

Forecast Accuracy of Naïve Model vs. Modified Naive Model

- Forecast Accuracy Interpretation
• A forecast error is considered small or large?
 Consider all sets of Forecast Accuracy MAD, MSE, RMSE, MAPE
 Every forecast value is deviated an average value of___MAD_____
 If the percentage error MAPE is low, close to zero, the every forecast
value is not biased by a percentage of _a%__
• A smaller accuracy measures indicates a better fit of the
model to the data

11

5
 10/1/2024

Associative Forecasting - Regression Analysis

• Based on identification of related variables that can be
used to predict values of the variable of interest.
 Sales of bikes in an area may be related to the percentage of
the young population living in that area.
 Ice cream sales can be related to temperature
 House sales forecasts on mortgage refinancing rates,
smaller rates imply higher sales.
 Changes in interest rate leads to certain business activities
– House sales
– Industrial investments
 Increase in energy cost leads to price increases in products
and services

Associative Forecasting - Regression Analysis

• Find an association between the predictor and the

predicted
• Predictor variables - used to predict values of variable
interest, sometimes called independent variables
• Predicted variable = Dependent variable
• Regression - technique for fitting a line to a set of
points
• Linear regression is the most widely used form of
regression
 The objective is to obtain an equation of a straight line that minimizes
the sum of squared vertical deviations of data points from the line.

6
 10/1/2024

Associative Forecasting - Regression Analysis

• Regression analysis established a temporal
relationship for the forecast variable.
 The variable to be predicted (demand) is referred to as the
dependent variable
 The variable of time-stamp (dấu thời gian) used in predicting
is called the independent variable.
• The simplest of relationship is a linear regression.
• The basic equation for the straight line that express
demand (Y) as a function of time (t) is
Yt   0  1t   t
Yt  b0  b1t
Yt   0  1 X t   t
14

Regression Analysis: Trend Models

• Three three trend model types are especially useful in forecasting:

Yt  b0  b1t for t  1, 2, , n linear trend

All three models can be
Yt  b0 eb1t for t  1, 2, , n exponential trend fitted by Excel,
Y  b  b t  b t 2 for t  1, 2, , n quadratic trend InputAnalyzer, MINITAB,
t 0 1 2
Matlab
𝑌 : dependent variable at time t
b0: constant term
b1: linear coefficient (quad) / Growth rate (expo)
b2: quadratic coefficient
• Trend model types are the simplest model and may suffice for short-run
forecasting or as a baseline model (the first simple attempt at modelling
which provides a baseline metric as a reference point)
• Linear model:
 a straight-line relationship between the independent variable (often time) and
the dependent variable.
 Use when the data shows a constant rate of change over time.
15

7
 10/1/2024

Regression Analysis: Trend Models

• Quadratic Trend Model: Yt  b0  b1t  b2t 2 for t  1, 2, , n quadratic trend
 the relationship between the independent and dependent
variable is represented by a second-degree polynomial.
 Use when the data shows a curve, with the rate of change in
the dependent variable increasing or decreasing over time.
• Exponential Trend Model: Yt  b0 eb1t for t  1, 2, , n exponential trend
 The dependent variable grows or declines at a constant
percentage rate over time.
 Use when the data shows exponential growth or decay, such
as population growth or compound interest
• Any trend model’s forecasts become less reliable as
they are extrapolated farther into the future.

16

Regression Analysis: Assessing Fit

• Several methods and metrics used for assessing the fit of a
regression model:
 Coefficient of Determination (R2):
͟ R2 represents the proportion of the variance in the dependent variable that is
predictable from the independent variable(s).
͟ Values of R2 range from 0 to 1; a higher indicates a better fit. However, R2 can be
artificially high if overfitting occurs.
 Adjusted *R2:
͟ Similar to R2 but adjusts for the number of predictors in the model.
 MAD, MSE, RMSE, MAPE:
͟ These metrics provide a measure of the average error in the model predictions.
͟ Lower values indicate better fit,
͟ especially useful when comparing different models.
 Residual Plots:
͟ Plotting residuals (the differences between observed and predicted values) can help
assess the fit.
 Normality of Residuals:
͟ For inference purposes, the residuals should ideally follow a normal distribution.
͟ Histograms, Q-Q plots, or statistical tests like the Shapiro-Wilk test can be used to
assess the normality of residuals.
 F-Test in ANOVA, T-Tests for Individual Coefficients, Durbin-Watson
17
Test, AIC and BIC

8
 10/1/2024

Techniques for Averaging

• Simple Averages
• Moving averages (MA)
 Naïve methods just trace the actual data with a lag of one period. They don’t
smooth
 MA uses a number of the most recent actual data to smooth
 Advantage=Easy to compute and easy to understand
 Disadvantage=All values in the average are weighted equally

• Weighted moving averages

 Similar to moving average
 It assigns more weight to the most recent values in a time series
 Idea: most recent observations must be better indicators of the
future than older observations
• Exponential smoothing

Simple Averages
• A simple average or simple moving average (SMA) uses the
mean of all relevant historical observations to compute the
initialization part of the data and to forecast the next period
t

Initialization Y  Y  ...  Yt Y i

part: Yˆt 1  1 2  i 1
t t
where: 𝑌 = forecast made at for period t for time/period t+1 ,
Yi = actual demand in periods i,
t = number of time periods which we count

• SMA is used when the forces generating the series to be

forecast have stabilized and the environment in which the
series exists is generally unchanging.

19

9
 10/1/2024

Moving Averages (MAs)

• Simple moving averages (SMA) uses the mean of all the data to
forecast while moving averages (MAs) is more concerned with
recent observations, that means a new mean is computed by
adding the newest value and dropping the oldest.
• By definition,
 MAs - moving averages are a series of averages calculated using sequential
segments of data points over a series of values.
 Segments have a moving length, which defines the number of data points to
include in each average.
• Moving averages can
 smooth time series data,
 remove seasonal patterns and reveal underlying trends
• Smoothing
 is the process of removing random variations that appear as coarseness in a
plot of raw time series data.
 reduces the noise to emphasize the series that can contain trends and
cycles.
20

Moving Averages (MA) or Trailing Moving Average (TMA)

• A moving average of order k, MA(k), is the mean value of

k consecutive observations.is computed by
k

Y  Y  Y  ...  Yt  k 1 Y t i 1
Yˆt 1  t t 1 t  2  i 1
k k
where: 𝑌 = forecast demand for period t+1
Yt-i = actual demand in periods t-i
k = number of terms in the moving average
• The moving average for time period t is the arithmetic
mean of the k most recent observations.
• The moving average model does not handle trend or
seasonality very well, although it does better than the
simple average method.
• The choice of the value of k should be determined by
experimentation and often lies within the ranges of 3 to 8.
21

10
 10/1/2024

Ex: Three period moving average forecast

Month Demand
1 42 MA(6,3) = (43 + 40 + 41) / 3
2 40 = 41.33.
3 43 If Y6 = 39, then
4 40 MA(7,3) = (40 + 41 + 39) / 3
5 41 = 40.00
6 39

Simple Moving Average

Note the sensitivity of forecasts
Averaging (over time) techniques are used to smooth variations in the data.

Actual
MA(t,5)
47
45
43
41
39
37
MA(t,3)
35
1 2 3 4 5 6 7 8 9 10 11 12
t

 Yi
Y t 1  MAt 1, k  i  t  k 1
,
k
MAt 1, k : MA forecast made in period t using n actual observations

11
 10/1/2024

Weighted average

Moving Average
• Advantage=Easy to compute and easy to
understand
• Disadvantage=All values in the average are
weighted equally

Weighted Moving Average

• Similar to moving average
• It assigns more weight to the most recent
values in a time series
 Idea: most recent observations must be better
indicators of the future than older observations

Weighted average

Compute a weighted average forecast using a

Month Demand weight of 0.4 for the most recent period, 0.3
1 42 for the next most recent, 0.2 for the next and
0.1 for the next.
2 40
3 43
Continuing with the data on the left
4 40 Y^6 = .40(41)+.30(40)+.20(43)+.10(40)=41.0
5 41 If the actual demand for period 6 is 39,
6 39 Y^7 = .40(39)+.30(41)+.20(40)+.10(43)=40.2

• The weighted average is more reflective of

the most recent occurrences.

12
 10/1/2024

Moving Averages (MA) or Trailing Moving Average (TMA)

• The number of points k used for the average increases,
the curve becomes smoother and smoother. Choosing a
value for k is a balance between eliminating noise while
still capturing the data’s true structure.
 A small number k is most desirable
 A small number k places heavy weight on recent historical
observations, that might catch up more rapidly to the current level
 A large number k is desirable when there are wide, infrequent
fluctuations in the series
 For smoothing out: MA(4) yields an average of the four quarters,
MA(12), eliminates or averages out the seasonal effects
• Minitab can be used to compute a k moving average
• Check the autocorrelation function for the residuals from
the k moving average method
26

Double Moving Averages (DMA)

• If time series has a linear trend we use Double Moving
Averages DMA which averages of moving averages, that
means
 One set of moving averages is computed, and
 then a second set is computed as a moving average of the first set
• First, compute the moving average of order k Count an amount of k, use
the subscript k= 0…1…2…k-1

• Second, compute the second moving average

One set of moving averages is computed, and then a second set is

computed as a moving average of the first set
27

13
 10/1/2024

Double Moving Averages (DMA)

• Third, calculate a forecast by DMA, compute the
coefficient of the “linear trend line” by adding to the single
moving average Mt the difference between the single and
the second moving averages (Mt-M’t), we get

• Fourth, compute an additional adjustment factor, which is

similar to a slope measure that can change over the series
where
k = the number of periods in the
moving average

• Last, make the forecast p periods into the future Y t  p  at  bt p

where
p = the number of periods ahead to be forecast
28

Centered Moving Average (CMA)

• The Centered Moving Average smoothing method

looks forward and backward in time to express the
current “forecast” as a mean of the current
observation and observations on either side of the
current data.
• Therefore, when calculating a simple moving average,
it is beneficial to use an odd number of points (k) so
that the calculation is symmetric
• For example, using k = 3 periods, the CMA is:
a 5 point moving average

29

14
 10/1/2024

Centered Moving Average (CMA)

• When k is odd (k = 3, 5, etc.), the simple moving average is
easy to calculate.
• When k is even, the mean of an even number of data points
would lie between two data points and would not be correctly
centered.
 In this case, we would take a double moving average to get the
resulting CMA centered properly.
• Centered moving averages (CMA) are computed by
averaging across data both in the past and future of a given
time point.
• Therefore, they cannot be used for forecasting because at
the time of forecasting (because the future is typically
unknown)
30

Centered Moving Average (CMA)

Time Period Data Value
2022 Quarter I 818
2022 Quarter II 861
2022 Quarter III 844
2022 Quarter IV 906 𝑌 𝑌
2023 Quarter I 867
2023, Quarter II 899
• k=3, 3-Quarter Centered Moving Average for 2022, Quarter IV:
 844  906  867  872.3
𝑌
3
• k=4, 4-Quarter Centered Moving Average for 2022, Quarter IV:

𝑌  0.5861 844  906  867  0.5844  906  867  899  874.25

4 4

31

15