Financial time series_forecasting_svm
-
Upload
mohamed-dhaoui -
Category
Data & Analytics
-
view
101 -
download
2
Transcript of Financial time series_forecasting_svm
Tunisia Polytechnic School
Data Mining project
Presented by
Mohamed DHAOUI
3rd year engineering student
([email protected]) Academic Year : 2015-2016
Financial time series forecasting using support vector machines
2
◦
◦
◦
3
4
5
6
7
8
9
10
11
12
13
a weight parameter, which needs to be carefully set
14
15
16
17
18
19
20
21
22
23
24
25
26
27
Backpropagation, an abbreviation for "backward propagation of errors", is a common method of training artificial neural networks used in conjunction with an optimasition method such as gradient descent. The method calculates the gradient of a loss function with respect to all the weights in the network and try to update these weights,
28
29
Algorithm:
initialize network weight (randomly)
Do
forEach training example ex
prediction = neural-net-output(network, ex)
actual = teacher-output(ex)
compute error (prediction - actual) at the output units
compute for all weights
update network weights
until all examples classified correctly or another stopping criterion satisfied
return the network
30
Weights updating
Δwt = -e* E + α Δwt-1
=H* δ0
e: learning rate
α :momentun
Wh,o
Hidden layer
Output layer
O
HE= actual-ideal
δ0= -E*f’(o)
δk= f’(h)*Wh,o *δ0
31
Weaknesses
• Gradient descent with backpropagation is notguaranteed to find the global minimum.
• There is no rule for selecting the bestlearning rate and the momentum.
• Slow algorithm that need a computationalresources.
32
SVM perfermance
• Too small value for C caused underfit the training data while too large a value of C caused overfit the training data
33
the best prediction performance of the holdout data is recorded when delta is 25 and C is 78
SVM perfermance
34
BP perfermance
• The best prediction performance for the holdout data is produced when the number of hidden processing elements are 24 and the stopping criteria is 146 400 epochs.
• The prediction performance of the holdout data is 54.7332% and that of the training data is 58.5217%.
35
Comparison
SVM outperforms BPN and CBR by 3.0981% and 5.852% for the holdout data, respectively
For the training data, SVM has higher prediction accuracy than BPN by 6.2309%
SVM performs better than CBR at 5% statistical significance level
SVM does not significantly outperform BP BP and CBR do not significantly outperform each
other
36