Empirical comparison of supervised learning techniques for missing value imputation

Knowledge and Information Systems - Many data mining algorithms cannot handle incomplete datasets where some data samples are missing attribute values. To solve this problem, missing value...     

Feature selection in bankruptcy prediction

For many corporations, assessing the credit of investment targets and the possibility of bankruptcy is a vital issue before investment. Data mining and machine learning techniques have been applied to solve the bankruptcy prediction and credit scoring problems. As feature selection is an important step to select more representative data from a given dataset in data mining to improve the final prediction performance, it is unknown that which feature selection method is better. Therefore, this paper aims at comparing five well-known feature selection methods used in bankruptcy prediction, which are t-test, correlation matrix, stepwise regression, principle component analysis (PCA) and factor analysis (FA) to examine their prediction performance. Multi-layer perceptron (MLP) neural networks are used as the prediction model. Five related datasets are used in order to provide a reliable conclusion. Regarding the experimental results, the t-test feature selection method outperforms the other ones by the two performance measurements.     

Using neural network ensembles for bankruptcy prediction and credit scoring

Bankruptcy prediction and credit scoring have long been regarded as critical topics and have been studied extensively in the accounting and finance literature. Artificial intelligence and machine learning techniques have been used to solve these financial decision-making problems. The multilayer perceptron (MLP) network trained by the back-propagation learning algorithm is the mostly used technique for financial decision-making problems. In addition, it is usually superior to other traditional statistical models. Recent studies suggest combining multiple classifiers (or classifier ensembles) should be better than single classifiers. However, the performance of multiple classifiers in bankruptcy prediction and credit scoring is not fully understood. In this paper, we investigate the performance of a single classifier as the baseline classifier to compare with multiple classifiers and diversified multiple classifiers by using neural networks based on three datasets. By comparing with the single classifier as the benchmark in terms of average prediction accuracy, the multiple classifiers only perform better in one of the three datasets. The diversified multiple classifiers trained by not only different classifier parameters but also different sets of training data perform worse in all datasets. However, for the Type I and Type II errors, there is no exact winner. We suggest that it is better to consider these three classifier architectures to make the optimal financial decision.     

Preliminary cost estimates for thin-film transistor liquid–crystal display inspection and repair equipment: A hybrid hierarchical approach

The thin-film transistor liquid–crystal display (TFT-LCD) industry has developed rapidly in recent years. Because TFT-LCD manufacturing is highly complex and requires different tools for different products, accurately estimating the cost of manufacturing TFT-LCD equipment is essential. Conventional cost estimation models include linear regression (LR), artificial neural networks (ANNs), and support vector regression (SVR). Nevertheless, in accordance with recent evidence that a hierarchical structure outperforms a flat structure, this study proposes a hierarchical classification and regression (HCR) approach for improving the accuracy of cost predictions for TFT-LCD inspection and repair equipment. Specifically, first-level analyses by HCR classify new unknown cases into specific classes. The cases are then inputted into the corresponding prediction models for the final output. In this study, experimental results based on a real world dataset containing data for TFT-LCD equipment development projects performed by a leading Taiwan provider show that three prediction models based on HCR approach are generally comparable or better than three conventional flat models (LR, ANN, and SVR) in terms of prediction accuracy. In particular, the 4-class and 5-class support vector machines in the first-level HCR combined with individual SVR obtain the lowest root mean square error (RMSE) and mean average percentage error (MAPE) rates, respectively.     

Popular research topics in multimedia

Multimedia has taken on a very important role in our daily life which has led to a rapid growth research on this topic. Multimedia research covers a variety of problem domains so one must examine many current popular research areas to obtain a basic understanding of current multimedia research. This allows us to understand what has been done recently and to consider what will be more important in future. In this study, we collect and analyze data from ACM Multimedia conferences from 2007 to 2011. In particular, the organized sessions (or areas) and the citation count of popular areas are examined using the Web of Science and Google Scholar. Then, the self-organizing map method is used as a visualization tool for keyword analysis in order to identify popular areas and research topics in multimedia. In addition, we also examine the consistency of the identified popular research areas and topics between the ACM Multimedia conferences and two recent journal special issues.     

A hybrid financial analysis model for business failure prediction

Accounting frauds have continuously happened all over the world. This leads to the need of predicting business failures. Statistical methods and machine learning techniques have been widely used to deal with this issue. In general, financial ratios are one of the main inputs to develop the prediction models. This paper presents a hybrid financial analysis model including static and trend analysis models to construct and train a back-propagation neural network (BPN) model. Further, the experiments employ four datasets of Taiwan enterprises which support that the proposed model not only provides a high predication rate but also outperforms other models including discriminant analysis, decision trees, and the back-propagation neural network alone.     

The development of audit detection risk assessment system: Using the fuzzy theory and audit risk model

The result of audit designation is significantly influenced by the audit evidence collected when planning the audit and the amount of audit evidence depends on the degree of detection risk. Therefore, when the assessment factors of detection risk are more objective and correct, audit costs and the risk of audit failure can be reduced. Thus, the aim of this paper is to design an audit detection risk assessment system that could more precisely assess detection risk, comparing with the traditional determination method of detection risk in order to increase the audit quality and reduce the possibility of audit failure. First of all, the grounded theory is used to reorganize 53 factors affecting detection risk mentioned in literatures and then employed the Delphi method to screen the 43 critical risk factors agreed upon by empirical audit experts. In addition, using the fuzzy theory and audit risk model to calculate the degree of detection risk allow the audit staff to further determine the amount of audit evidence collected and set up initial audit strategies and construct the audit detection risk assessment system. Finally, we considered a case study to evaluate the system in terms of its feasibility and validity.     

Component-based software version management based on a Component-Interface Dependency Matrix

As much component-based software is developed, a software configuration management (SCM) tool for component-based software is necessary. In this paper, we propose a version management mechanism for impact analysis while components are upgraded. We separately version the components and interfaces based on a Component-Interface Dependency Matrix (CIDM), and analyze impacts according to their dependency relationship. The result of our simulation shows that CIDM is capable of managing large numbers of components without impedance mismatch. In addition, in a well-designed software system, using CIDM to analyze impacts can save resources in the software development phase.     

Intrusion detection by machine learning: A review

The popularity of using Internet contains some risks of network attacks. Intrusion detection is one major research problem in network security, whose aim is to identify unusual access or attacks to secure internal networks. In literature, intrusion detection systems have been approached by various machine learning techniques. However, there is no a review paper to examine and understand the current status of using machine learning techniques to solve the intrusion detection problems. This chapter reviews 55 related studies in the period between 2000 and 2007 focusing on developing single, hybrid, and ensemble classifiers. Related studies are compared by their classifier design, datasets used, and other experimental setups. Current achievements and limitations in developing intrusion detection systems by machine learning are present and discussed. A number of future research directions are also provided.