Académique Documents
Professionnel Documents
Culture Documents
• Naïve approach
• Moving averages Time-series
• Exponential smoothing Models
• Trend projection
Associative
• Linear regression models
What is a Time Series?
• Set of evenly spaced numerical data
– Obtained by observing response variable at regular time
periods
• Forecast based only on past values
– Assumes that factors influencing past and present will
continue influence in future
• Example
Year: 1998 1999 2000 2001 2002
Sales: 78.7 63.5 89.7 93.2 92.1
Time Series Components
Trend Cyclical
Seasonal Random
Trend Component
• Persistent, overall upward or downward
pattern
• Due to population, technology etc.
• Several years duration
Seasonal Component
• Regular pattern of up & down fluctuations
• Due to weather, customs etc.
• Occurs within 1 year
Common Seasonal Patterns
Period of “Season” Number of
Pattern Length “Seasons” in
Pattern
Week Day 7
Month Week 4–4½
Month Day 28 – 31
Year Quarter 4
Year Month 12
Year Week 52
Cyclical Component
• Repeating up & down movements
• Due to interactions of factors influencing
economy
• Usually 2-10 years duration
Random Component
• Erratic, unsystematic, ‘residual’ fluctuations
• Due to random variation or unforeseen events
– Union strike
– Tornado
5-month
125 –
100 –
Orders
75 –
50 – 3-month
Actual
25 –
0– | | | | | | | | | | |
Jan Feb Mar Apr May June July Aug Sept Oct Nov
Month
Weighted Moving Average
Adjusts WMAn = Wi Di
i=1
moving
average where
method to Wi = the weight for period i,
more closely between 0 and 100
percent
reflect data
fluctuations W = 1.00
i
Weighted Moving Average Example
= 103.4 orders
Exponential Smoothing
Ft +1 = Dt + (1 - )Ft
Averaging method where
Weights most Ft +1 = forecast for next
recent data more period
strongly Dt = actual demand for
Reacts more to present period
recent changes Ft = previously
determined forecast
Widely used, for present period
accurate method
= weighting factor,
smoothing constant
Effect of Smoothing Constant
60 – Actual = 0.50
50 –
Orders
40 –
= 0.30
30 –
20 –
10 –
| | | | | | | | | | | | |
0–
1 2 3 4 5 6 7 8 9 10 11 12 13
Month
Forecast Accuracy
Error = Actual - Forecast
Find a method which minimizes error
Mean Absolute
Deviation (MAD)
Mean Absolute
Percent Deviation (MAPD)
Cumulative Error (E)
The MAD Statistic to Determine
Forecasting Error
n
1 MAD 0.8 standard deviation
A
t=1
t - Ft
1 standard deviation 1.25 MAD
MAD =
n
(Dt - Ft) E
Tracking signal = =
MAD MAD