An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best...
Transcript of An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best...
![Page 1: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/1.jpg)
An evaluation of simple vs. complex selection
rules for forecasting many time series
Fotios Petropoulos
Prof. Robert Fildes
![Page 2: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/2.jpg)
Outline
• Introduction
• Research Questions
• Experimental set-up: methods, data & rules
• Empirical investigation
• Implications & limitations
• Conclusions & perspectives
![Page 3: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/3.jpg)
Introduction
• Forecasters regularly face the question of choosing from a
set of alternative forecasting methods.
• The forecasting methods usually considered are simple.
• Two distinct approaches have been proposed for dealing
with this problem (Fildes, 1989):
• aggregate selection
• individual selection
• The main objective of the current research is to investigate
the conditions under which individual model selection may
be beneficial.
![Page 4: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/4.jpg)
Why is individual method selection important?
• If individual selection could be done perfectly, the gains over
the best ex-post aggregate selection would be substantial.
• Improvements in univariate forecasting accuracy financially
valuable.
• Results of various competitions:
• no single best method
• wide divergence in comparative performance by series
• within homogeneous data sets unexpected methods
dominate
• The alternative: to develop a new general method. Is this
feasible?
![Page 5: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/5.jpg)
Research Questions (1)
• Segmenting the data:
• Predictable/Unpredictable • Is the performance of non-seasonal Random Walk
forecasting method is better than the median performance
of all other methods under investigation as defined by
Mean Absolute Error in the validation data?
• Trended/Non-Trended • Cox-Stuart test over a 12-period centered moving average
• Seasonal/Non-Seasonal • Friedman’s non-parametric test
RQ1. Is individual model selection more effective when
applied to groups of time series with specific characteristics?
![Page 6: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/6.jpg)
Research Questions (2)
RQ2. What are the effects on individual selection of including
more methods in the pool under consideration?
• Number of models included in the pool of alternatives.
• Effectively a variant of over-fitting, the more models
included, the higher the probability that the wrong model is
chosen due to the randomness in the data.
• Every possible combination of smaller pools of two (2) up to
twelve (12) methods is also examined.
• For example, in the case of a pool of methods equal to
four (4), all 495 possible pools of methods are checked,
the number of 4-combination in a set of 12
![Page 7: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/7.jpg)
Research Questions (3)
• Many of the methods included in typical extrapolative
competitions produce similar forecasts.
• Selection between methods that produce similar forecasts
cannot prove valuable.
• Selecting among methods with low to medium correlated
outputs and similar levels of accuracy is intuitively more
promising.
RQ3. Do pools of methods with low correlation, in terms of
forecast error, provide better forecasting performance when
individual selection rules are considered compared to more highly
correlated pools?
![Page 8: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/8.jpg)
Research Questions (4)
• Individual selection would be unlikely to be beneficial when a
single method is dominant.
• Identify sub-populations where a dominant method exists (or
not).
• Divide the data series into two groups in terms of the
performance of one of the best methods.
• 1st Group (Dominant method): Theta’s performance in the top
three
• 2nd Group (Non-dominant method): Theta’s performance
outside the top three
RQ4. Individual method selection is of most value when no
dominant method is identified across the population.
![Page 9: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/9.jpg)
Research Questions (5)
• The performance of the different methods is also analysed
for their stability.
• Stability in a specific series can be measured by the average
(across time origins) Spearman’s rank correlation coefficient.
• A series is defined as stable when its Spearman’s rho falls in
the top quartile of the data set.
RQ5. Individual selection is only effective compared to aggregate
selection when relative performance in the pool of methods under
consideration is stable.
![Page 10: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/10.jpg)
How to choose a ‘best’ method?
• In-sample fit rules
• MSE, AIC, BIC etc
• Makes intuitive sense, but on its own has poor
predictive properties (Pant & Starbuck, 1990).
• Out-of-sample rules
• Makes even more sense: what has forecast the most
accurately, will forecast the most accurately.
• Complex selection rules
• Based on numerous data characteristics & combination
approaches (for example, Collopy & Armstrong, 1992;
Shah, 1997; Meade, 2000).
![Page 11: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/11.jpg)
Selection Rules (individual selection)
Rule 1. Use the method with best fit as measured by the minimum one-
step ahead in sample Mean Squared Error.
Rule 2. Use the method with the best out-of-sample one-step-ahead
forecast error, in terms of Mean Absolute Percentage Error.
Rule 3. Use the method with best out-of-sample h-step-ahead forecast,
in terms of Mean Absolute Percentage Error, and apply this method to
forecast for just the same lead time.
Rule 4. Use the best out-of-sample 1-18-steps-ahead, in terms of Mean
Percentage Absolute Error, method to forecast for all lead times.
![Page 12: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/12.jpg)
Benchmarks
The empirical results focus on comparing the performance of individual
selection versus the two simple benchmarks:
• Aggregate selection: this uses the single best method based on the
one-step-ahead out-of-sample performance on the validation sample
• The combination of methods applying equal weights to each method
included in the selection pool.
![Page 13: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/13.jpg)
The set-up: data & methods
• M3 data
• monthly frequency
• 126 or more observations
• n = 998 series
48 obs
Initialization
42 obs
Selection
36 obs
Evaluation
Rolling Forecasting:
18 forecasts ahead are
calculated for each origin
T1 T2
• Methods: Naïve, SES, Holt, Damped, Holt-Winters,
Theta, ARIMA
![Page 14: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/14.jpg)
Individual selection approaches:
A graphical illustration
48 obs 42 obs
36 obs
![Page 15: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/15.jpg)
Individual selection approaches:
A graphical illustration
48 obs
![Page 16: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/16.jpg)
Individual selection approaches:
A graphical illustration
49 obs
![Page 17: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/17.jpg)
Individual selection approaches:
A graphical illustration
50 obs
![Page 18: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/18.jpg)
Individual selection approaches:
A graphical illustration
89 obs
![Page 19: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/19.jpg)
Individual selection approaches:
A graphical illustration
miPFPiMethodBest m
kTTAPEkT ,6,1|minarg timeslead allfor |_ 1, 212
![Page 20: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/20.jpg)
Individual selection approaches:
A graphical illustration
miPFPiMethodBest m
kTTAPEkT ,6,1|minarg timeslead allfor |_ 1, 212
![Page 21: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/21.jpg)
Individual selection approaches:
A graphical illustration
miPFPiMethodBest m
kTTAPEkT ,6,1|minarg timeslead allfor |_ 1, 212
![Page 22: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/22.jpg)
Individual selection approaches:
A graphical illustration
90 obs
miPFPiMethodBest m
kTTAPEkT ,6,1|minarg timeslead allfor |_ 1, 212
![Page 23: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/23.jpg)
Individual Selection vs Aggregate Selection & Combination % of cases improved when all series are considered
Me
tho
ds
in
se
lec
tio
n
po
ol
Ave
rag
e C
orr
ela
tio
n
Nu
mb
er
of
ca
se
s % of cases Individual Selection performed better
vs. Aggregate vs. Combination
Rule
1
Rule
2
Rule
3
Rule
4
Rule
1
Rule
2
Rule
3
Rule
4
2-4 Low 611 31.3 65.0 44.4 86.4 33.4 75.0 83.1 90.0
High 170 13.5 65.3 55.3 75.3 18.8 60.6 70.6 80.6
5-8 Low 2712 17.4 51.5 47.7 92.7 38.6 80.7 89.5 97.5
High 291 4.8 78.7 62.2 90.7 9.6 84.5 82.1 95.9
9-12 Low 295 3.7 46.4 41.7 97.6 45.1 91.2 95.3 100.0
High 4 0.0 100.0 25.0 100.0 25.0 100.0 100.0 100.0
![Page 24: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/24.jpg)
Best Practices
Segment Best Practice
Entire Data Set Individual selection (Rule 4) applied on a high number of low correlated methods
Predictable Combination applied on medium number of high correlated methods
Unpredictable Individual selection (Rule 4) applied on a high number of high correlated methods
Trended Individual selection (Rule 4) applied on a high number of high correlated methods
Non-Trended Combination applied on a medium number of high correlated methods
Seasonal Individual selection (Rule 3) applied on a medium number of high correlated methods
Non-Seasonal Combination applied on a medium number of high correlated methods
Dominant method Aggregate selection applied on a small number of high correlated methods
Non-dominant
method Aggregate selection applied on a medium number of high correlated methods
Stable Individual selection (Rule 4) applied on a high number of low correlated methods
Unstable Combination applied on a high number of high correlated methods
![Page 25: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/25.jpg)
Accuracy improvements (MdAPE %)
Ag
gre
ga
te
Sele
cti
on
Co
mb
ina
tio
n
Ind
ivid
ua
l
Se
lec
tio
n
Me
dia
n
Pe
rfo
rma
nc
e o
f
Be
st
Pra
cti
ce
DD
am
p
(Be
nc
hm
ark
)
Imp
rove
me
nt
Entire Data Set 7.4% 7.6% 7.2% 7.1% 7.5% 4.8%
Predictable 6.5% 6.9% 6.6% 6.4% 6.6% 2.7%
Unpredictable 9.1% 8.8% 8.7% 8.4% 9.5% 11.4%
Trended 6.8% 7.0% 6.8% 6.7% 6.9% 2.4%
Non-Trended 14.9% 15.8% 15.2% 14.6% 15.1% 3.3%
Seasonal 9.2% 9.5% 9.0% 8.9% 9.2% 3.0%
Non-Seasonal 4.5% 4.4% 4.6% 4.4% 4.5% 2.1%
Dominant Method 7.8% 8.4% 7.9% 8.0% 8.2% 2.5%
Non-dominant
method 6.7% 6.9% 6.8% 6.6% 6.8% 3.0%
Stable 6.9% 7.8% 6.8% 6.6% 6.9% 4.1%
Unstable 7.6% 7.6% 7.6% 7.5% 8.1% 7.7%
![Page 26: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/26.jpg)
Implications & Limitations
• Enhance the integrated automatic selection procedures.
• Best practices indicate a mix of simple and easy to apply approaches
with more complicates selection schemes.
• Computational intensive → specialized system design .
• Limited data history available.
• Data coming from a specific industry might appear more
homogeneous.
• Adjustments in the design → defining useful segments.
![Page 27: An evaluation of simple vs. complex selection rules for forecasting … · 2017-04-07 · the best ex-post aggregate selection would be substantial. •Improvements in univariate](https://reader033.fdocuments.us/reader033/viewer/2022042406/5f20e51995f3ef34c679c736/html5/thumbnails/27.jpg)
Conclusions
• Segmenting the series enables identifying suitable sub-populations of
data, where the application of individual selection is more effective.
• Improvements from individual selection over aggregate selection are
recorded when small to medium pools of methods are considered.
• Aggregate selection produces the best results when a single method
displays dominant performance across a specific sample of series.
• Individual selection produces more accurate forecasts, when series are
identified as stable. However, for the unstable series, the combination of
methods is the most robust choice.
• The selection rule relying to the forecast performance over all horizons
(Rule 4) proved better, while simply relying on past in-sample performance
over the fitted data proved inadequate.
• Next step: Enhance the selection rules by using a large number of
variables proposed in the literature to characterise a time series.