Feature Weighting of Support Vector Machines Based on Derivative Saliency Analysis and Its Application to Financial Data Mining

@article{Shen2012FeatureWO,
  title={Feature Weighting of Support Vector Machines Based on Derivative Saliency Analysis and Its Application to Financial Data Mining},
  author={Chuanhe Shen and Xiangrong Wang and Di Yu},
  journal={International Journal of Advancements in Computing Technology},
  year={2012},
  volume={4},
  pages={199-206}
}
Abstract This paper proposes a novel feature weighting approach based on derivative saliency analysis, which can specifically display to what extent the output of support vector regression machines varies with the features (i.e. the components of the input vector). The empirical analysis of its application to option pricing demonstrates that the methodology proposed enables relevant features to be assigned right weights under given generation performance error criterion. At the same time, a… Expand
On the evolutionary optimization of k-NN by label-dependent feature weighting
TLDR
An evolutionary approach called k-Label Dependent Evolutionary Distance Weighting (kLDEDW) is shown which calculates a set of local weights depending on each class besides an optimal k value which improves the general k-nearest-neighbour rule and several approaches based on local weighting. Expand
Multi-Objective Evolutionary Optimization Algorithms for Machine Learning: A Recent Survey
TLDR
Recent multi-objective evolutionary approaches for four major data mining and machine learning tasks, namely: (a) data preprocessing, (b) classification, (c) clustering, and (d) association rules, are surveyed. Expand
Data preprocessing in predictive data mining
TLDR
This work presents the most well-known and widely used up-to-date algorithms for each step of data preprocessing in the framework of predictive data mining. Expand
Bayesian Support Vector Machines for Economic Modeling: Application to Option Pricing
An option is the right, not the obligation, to buy or sell an underlying asset at a later date by fixing the price of the asset at the present moment. European styled options can be priced using theExpand
A New Framework for Nonlinear Cointegration Analysis and Its Application to Finance
TLDR
The empirical analysis demonstrates that the support vector machine is effective in analyzing the money function and its stability and has advantages in dealing with nonlinear cointegration relations and estimating nonlin- ear functions over the two methods above. Expand
Economic Modeling Using Artificial Intelligence Methods
  • T. Marwala
  • Computer Science
  • Advanced Information and Knowledge Processing
  • 2013
TLDR
Economic Modeling Using Artificial Intelligence Methods deals with the issue of causality in the non-linear domain and applies the automatic relevance determination, the evidence framework, Bayesian approach and Granger causality to understand causality and correlation. Expand

References

SHOWING 1-10 OF 18 REFERENCES
A comparative study of saliency analysis and genetic algorithm for feature selection in support vector machines
  • F. Tay, L. Cao
  • Mathematics, Computer Science
  • Intell. Data Anal.
  • 2001
TLDR
This paper investigates the use of saliency analysis (SA) and genetic algorithm (GA) in SVMs for selecting important features in the context of regression estimation, and the derivation of the sensitivity of the network output to the feature input in terms of the partial derivative in SVM is presented. Expand
Correlation-based Feature Selection for Discrete and Numeric Class Machine Learning
TLDR
This paper describes a fast, correlation-based filter algorithm that can be applied to continuous and discrete problems and performs more feature selection than ReliefF does—reducing the data dimensionality by fifty percent in most cases. Expand
Parameter determination of support vector machine and feature selection using simulated annealing approach
TLDR
Experimental results indicate that the classification accuracy rates of the proposed approach exceed those of grid search and other approaches, and the SA-SVM is thus useful for parameter determination and feature selection in the SVM. Expand
Improving option price forecasts with neural networks and support vector regressions
TLDR
A simple and effective nonparametric method of forecasting option prices based on neural networks and support vector regressions is presented and extensive experimental studies with data from the Hong Kong option market demonstrated the ability of NNs and SVRs to improve forecast accuracy. Expand
Improving SVM by Modifying Kernel Functions for Speaker Identification Task
TLDR
An empirical comparison of kernel selection for SVM was used and performance on text-independent speaker identification using the TIMIT corpus showed that the best performance had been achieved by using polynomial kernel and reported a speaker identification rate equal to 82.47%. Expand
American option pricing using Bayesian multi-layer perceptrons and Bayesian support vector machines
  • M. M. Pires, T. Marwala
  • Computer Science
  • IEEE 3rd International Conference on Computational Cybernetics, 2005. ICCC 2005.
  • 2005
TLDR
It was found that Bayesian SVM's out-performed Bayesian MLP's and that there is scope for further work. Expand
Robust Feature Selection Using Ensemble Feature Selection Techniques
TLDR
It is shown that ensemble feature selection techniques show great promise for high-dimensional domains with small sample sizes, and provide more robust feature subsets than a single feature selection technique. Expand
Wrappers for Feature Subset Selection
TLDR
The wrapper method searches for an optimal feature subset tailored to a particular algorithm and a domain and compares the wrapper approach to induction without feature subset selection and to Relief, a filter approach tofeature subset selection. Expand
Choosing Multiple Parameters for Support Vector Machines
The problem of automatically tuning multiple parameters for pattern recognition Support Vector Machines (SVMs) is considered. This is done by minimizing some estimates of the generalization error ofExpand
Fuzzy Support Vector Machine Method for Evaluating Innovation Sources in Service Firms
TLDR
F fuzzy support vector machine method for innovation sources in service firms provides a new way in the process of selecting innovation sources, and shows higher accuracy rate and lower error rate. Expand
...
1
2
...