Search

• Exploring the effect of locally weighted learning with machine learning model. • Gain ratio are used to select the most important environmental factor. • LWL-RS-ADT appears as an accurate model in assessing landslide susceptibility. Assessing landslide susceptibility and predicting the possibility of landslide event is the foundation and prerequisite for emergency response and management of landslide disaster. The target of current paper is to propose five integration models based on integrating locally weighted learning (LWL) with a radial basis function classifier (RBF), Fisher's linear discriminant (FLDA), quadratic discriminant analysis (QDA), a Credal decision tree (CDT), an alternating decision tree (ADT) and random subspace (RS) and the performance of five integration models were compared for modeling landslide susceptibility. Yongxin County from China was employed as a study area, 364 landslide locations and fifteen environmental factors were applied. The results demonstrate that the proposed LWL-RS-ADT model is more reliable and stable than the other models. Among the fifteen environmental factors, NDVI, lithology, and altitude are the very significant factors in the six models. It is concluded that the proposed integration models provide an effective way to predict the susceptibility of landslides. [ABSTRACT FROM AUTHOR]

Predicting the stock price is challenging because of its volatility, high dimensions, and complex non-linearity. The multitask learning methods can capture the internal relationship among sub-tasks and obtain better prediction effect than the traditional single-task learning methods. However, most multitask learning methods ignore the inherent distribution of the original samples, which fails at achieving good generalization performance. In this paper, we first present an asymmetric squared ɛ -insensitive loss function, which can improve the generalization ability of the regressor by adjusting the asymmetric parameter. Then, an asymmetric proximal support vector regression (a-PSVR) model is proposed, which greatly improves the flexibility of proximal support vector regression (PSVR). Based on different multitask learning assumptions, two multitask learning asymmetric proximal support vector regression algorithms, i.e., MTL-a-PSVR and EMTL-a-PSVR, are advanced. Both multitask learning algorithms can obtain optimal solutions by solving quadratic programming problems. Additionally, a special case of multitask learning proximal support vector regression (MTL-PSVR) is introduced by analyzing the asymmetric squared ɛ -insensitive loss function. To illustrate the merit of the methods, the proposed models are applied to predict the trends of stock market indices in China and the U.S. and stock prices of four Chinese securities companies. The experimental results demonstrate the significant advantages of the proposed algorithms in prediction effect and generalization performance. • An ɛ -insensitive loss function is presented for asymmetrically distributed data. • The a-PSVR has better prediction performance than proximal support vector regression. • A multitask joint learning model is proposed to perform the stock market forecast. • The cross-relations and asymmetry among stock data were considered simultaneously. [ABSTRACT FROM AUTHOR]

Advanced decision support for rail traffic control is significant for enhancing the safety and quality of railway transport service. Data-driven methods have shown powerful learning ability and wide extensibility for prediction, classification, and decision-making problems. In this paper, we propose a hybrid prediction model based on deep forest (DF) ensemble learning to analyze the two common rail traffic control actions, i.e., changing the dwelling times and running times. This basic concept is to mimic the decision-making of rail traffic controllers, providing them with advanced decisions/control actions using data-driven learning algorithms. According to the decision-making approach of rail traffic controllers, the learning process of the model is split into two stages, i.e., learning the type of action (ToA) and the number of changes (NoC) in the dwelling times and running times (i.e., how many dwelling times or running times have been changed compared with the planned ones). The first stage is a classification problem; thus, DF classifier with the synthetic minority oversampling technique (SMOTE) is employed to deal with imbalanced data. In the second stage, the DF regressor treats the NoC in the dwelling and running times as numerical variables and utilizes the information from stage one, i.e., the prediction results of the classification model, to make predictions. The proposed model is calibrated on train operation data from two high-speed railway lines in China. The experimental results and comparative analyses show that the proposed method provides advanced and timely decision support for controllers. These characteristics of the proposed model are imperative for supporting the dynamic decision-making of controllers to manage railway traffic. [ABSTRACT FROM AUTHOR]

• A faulty line detection method based on a lightweight depth separable convolution. • A data augmentation method based on a generative adversarial networks. • The proposed method has high accuracy of faulty line detection on small samples. • The effectiveness of the proposed method is verified by several experiments. This paper presents a small-sample faulty line detection method for a small current grounded system (SCGS) using improved generative adversarial networks (GANs) to overcome the problems of low accuracy and poor economy associated with traditional methods. First, we collected real-time fault data of the dispatching system as the original sample and used the linear interpolation and normalization methods to preprocess the data. We extracted and labeled the features of the original sample to construct a feature vector that represents the single-phase grounded fault. Then, to solve the problem of insufficient faulty samples, this paper used the GAN to generate synthetic samples to expand the training sample size. To stabilize the GAN training, the Wasserstein distance was introduced to improve the GAN loss function (WGAN). Finally, for the synthetic samples, we used Batch Normalization (BN) and an Early Stopping algorithm to train the lightweight depthwise separable convolutional network (DSCN) classifier and obtain a faulty line detection model with fast convergence and high accuracy. With the data of an actual dispatching system in China as an example, the proposed method determined the faulty line within 100–200 ms with an accuracy of more than 96%, which is approximately 26% higher than the accuracy of traditional methods. Compared with mainstream machine learning algorithms, the proposed method realizes the self-extraction of faulty features and simplifies the algorithm. Moreover, the accuracy of the proposed method is much higher than that of other machine learning algorithms on small samples. It is worth noting that this method needs only the existing real-time dispatching data and does not need to install additional data acquisition and fault detection equipment, eliminating the complicated equipment installation and debugging process and greatly reducing equipment costs human operations and maintenance costs. The proposed method has been implemented in an actual power system in China for two years. The results show that it is highly accurate and cost-effective, performs well in real time, and has bright prospects for future applications. [ABSTRACT FROM AUTHOR]

Integrating return prediction of traditional time series models in portfolio formation can improve the performance of original portfolio optimization model. Since machine learning and deep learning models have shown overwhelming superiority than time series models, this paper combines return prediction in portfolio formation with two machine learning models, i.e., random forest (RF) and support vector regression (SVR), and three deep learning models, i.e., LSTM neural network, deep multilayer perceptron (DMLP) and convolutional neural network. To be specific, this paper first applies these prediction models for stock preselection before portfolio formation. Then, this paper incorporates their predictive results in advancing mean–variance (MV) and omega portfolio optimization models. In order to present the superiority of these models, portfolio models with autoregressive integrated moving average's return prediction are used as benchmarks. Evaluation is based on historical data of 9 years from 2007 to 2015 of component stocks of China securities 100 index. Experimental results show that MV and omega models with RF return prediction, i.e., RF+MVF and RF+OF, outperform the other models. Further, RF+MVF is superior to RF+OF. Due to the high turnover of these two models, this paper discusses their performance after deducting the transaction fee cased by turnover. Experiments present that RF+MVF still performs the best among MVF models and omega model with SVR prediction (SVR+OF) performs the best among OF models. Moreover, RF+MVF performs better than SVR+OF and high turnover erodes nearly half of their total returns especially for RF+OF and RF+MVF. Therefore, this paper recommends investors to build MVF with RF return prediction for daily trading investment. • Compares the performance of machine learning and deep learning in stock preselection. • Combining return prediction of machine learning and deep learning in portfolio formation. • Emphasis on advancing portfolio optimization with return prediction. • Advanced mean–variance model with random forest forecasts performs the best. [ABSTRACT FROM AUTHOR]

• Propose an innovative Bayesian model to control the risk of COVID-19 patients. • Propose two indicators to verify the feasibility and effectiveness of the model. • Provide the tool for risk assessment in the field of epidemics. In the context of the outbreak of coronavirus disease (COVID-19), this paper proposes an innovative and systematic decision support model based on Bayesian networks (BNs) to identify and control the risk of COVID-19 patients spreading the virus, which requires the following three steps. First, by consulting the related literature and combining this with expert knowledge, we identify and classify the characteristics (risk factors) of COVID-19 and obtain a conceptual framework for COVID-19 Risk Assessment Bayesian Networks (CRABNs). Second, data on COVID-19 patients with expert scoring results on patient risk levels were collected from hospitals in Hubei Province of China and are used as the training set, and the structure and parameters of the CRABNs model are obtained through machine learning. Finally, we propose two indicators, namely, Model Bias and Model Accuracy, and use the remaining data to verify the feasibility and effectiveness of the CRABNs model to ensure that there are no significant differences between the predicted results of the model and the actual results provided by experts who have relevant experience in treating COVID-19. At the same time, we compared the CRABNs model with the support vector machine (SVM), random forest (RF), and k-nearest neighbour (KNN) models through four indicators: accuracy, sensitivity, specificity, and F-score. The results suggest the reliability of the model and show that it has promising application potential. The proposed model can be used globally by doctors in hospitals as a decision support tool to improve the accuracy of assessing the severity of COVID-19 symptoms in patients. Furthermore, with the further improvement of the model in the future, it can be used for risk assessments in the field of epidemics. [ABSTRACT FROM AUTHOR]

Since the booming development of e-commerce in the last decade, the researchers have begun to pay more attention to extract the valuable information from consumers comments. Sentiment classification, which focuses on classify the comments into positive class and negative class according to the polarity of sentiment, is one of the studies. Machine learning-based method for sentiment classification becomes mainstream due to its outstanding performance. Most of the existing researches are centered on the extraction of lexical features and syntactic features, while the semantic relationships between words are ignored. In this paper, in order to get the semantic features, we propose a method for sentiment classification based on word2vec and SVM perf . Our research consists of two parts of work. First of all, we use word2vec to cluster the similar features for purpose of showing the capability of word2vec to capture the semantic features in selected domain and Chinese language. And then, we train and classify the comment texts using word2vec again and SVM perf . In the process, the lexicon-based and part-of-speech-based feature selection methods are respectively adopted to generate the training file. We conduct the experiments on the data set of Chinese comments on clothing products. The experimental results show the superior performance of our method in sentiment classification. [ABSTRACT FROM AUTHOR]

Corporate financial distress prediction research has been ongoing for more than half a century, during which many models have emerged, among which ensemble learning algorithms are the most accurate. Most of the state-of-the-art methods of recent years are based on gradient boosted decision trees. However, most of them do not consider using feature importance for feature selection, and a few of them use the feature importance method with bias, which may not reflect the true importance of features. To solve this problem, a heuristic algorithm based on permutation importance (PIMP) is proposed to modify the biased feature importance measure in this paper. This method ranks and filters the features used by machine learning models, which not only improves accuracy but also makes the results more interpretable. Based on financial data from 4,167 listed companies in China between 2001 and 2019, the experiment shows that compared with using the random forest (RF) wrapper method alone, the bias in feature importance is indeed corrected by combining the PIMP method. After the redundant features are removed, the performance of most machine learning models is improved. The PIMP method is a promising addition to the existing financial distress prediction methods. Moreover, compared with traditional statistical learning models and other machine learning models, the proposed PIMP-XGBoost offers higher prediction accuracy and clearer interpretation, making it suitable for commercial use. • The model Combines a corrected feature selection measure and XGBoost. • Permutation importance can correct the bias of feature importance. • The model is validated on Chinese listed companies datasets over five metrics. • The model is proved to outperform several benchmark techniques. • The feature importance and partial dependence plot enhance model interpretation. [ABSTRACT FROM AUTHOR]

• European option datasets were time-sequenced by maturity to extract time information. • Two deep learning models were built for the option pricing tasks. • Our models can price option accurately without volatility calibration and simulation. • An interpretable method was used to find how models improved the pricing results. • Accumulate local effect range method was proposed to get feature emphasis of models. In this paper, we investigated the feasibility of pricing European options with time-sequencing data processing method and deep learning models, based on two European options, the ETF50 options of China and the S&P 500 options of America. Four competing models were built to verify the improvement of the 1D-CNN and LSTM models on the option pricing task. Methods like cross-validations and statistical tests were also used to make our experiments more robust. Besides, in order to increase the stability and the interpretability of our pricing models, we selected the ALE method to interpret and analyze the behavior of the deep learning models. The empirical results indicate that, in both ETF50 option and S&P500 option pricing tasks, the 1D-CNN and LSTM models had significant advantages in forecasting accuracy and robustness under moneyness, trading date or maturity dimension irrespectively. Especially for the LSTM model, which has robust performance using different kinds of cross-validation methods. With the help of ALE method, we proved that the improved performance brought by the 1D-CNN and LSTM models could be attributed to their capability of capturing time-series information and their different emphasis on input features and lags. [ABSTRACT FROM AUTHOR]

Abstract: In recent years, Gaussian process (GP) models have been popularly studied to solve hard machine learning problems. The models are important due to their flexible non-parametric modeling abilities using Mercer kernels and the Bayesian framework for probabilistic inference. In this paper, we propose a sparse GP regression (GPR) model for tourism demand forecasting in Hong Kong. The sparsification procedure of the GPR model not only decreases the computational complexity but also improves the generalization ability. We experiment the proposed model with monthly demand data that are relevant to Hong Kong’s tourism industry, and compare the performance of the sparse GPR model with those of various kernel-based models to show its effectiveness. The proposed sparse GPR model shows that its forecasting capability outperforms those of the ARMA model and the two state-of-the-art SVM models. [Copyright &y& Elsevier]

Abstract: The selection of assets in which to invest money is of critical importance in the finance industry, and is rendered very treacherous because of the inherent market fluctuations, and the connections with the Economy, and major world events. Because of the high dimensionality of the problem of selecting an optimal portfolio (in the financial sense of, a portfolio outperforming other portfolios), and the large amount of data available, intelligent systems (e.g. artificial intelligence techniques, machine learning approaches) are a natural approach to tackle this problem, from a computational standpoint. Numerous techniques have been developed to combine the values of return, risk, and other characteristics of an asset. However, the majority of techniques that have been used to construct a portfolio, tend to ignore dependencies among the characteristics of an asset. Moreover, most of the techniques assume that all available data are precise, which is not the case since, for instance, the expected return of an asset is a prediction of future behavior. To address these drawbacks, it was proposed in to use non-additive (or fuzzy) methods. Fuzzy methods outperformed other techniques, at least in the case of the Shanghai market, where full disclosure of information is assumed. In this paper, we give an intuition why fuzzy approach performs very well in this particular finance problem. [Copyright &y& Elsevier]

Abstract: Due to the important role of financial distress prediction (FDP) for enterprises, it is crucial to improve the accuracy of FDP model. In recent years, classifier ensemble has shown promising advantage over single classifier, but the study on classifier ensemble methods for FDP is still not comprehensive enough and leaves to be further explored. This paper constructs AdaBoost ensemble respectively with single attribute test (SAT) and decision tree (DT) for FDP, and empirically compares them with single DT and support vector machine (SVM). After designing the framework of AdaBoost ensemble method for FDP, the article describes AdaBoost algorithm as well as SAT and DT algorithm in detail, which is followed by the combination mechanism of multiple classifiers. On the initial sample of 692 Chinese listed companies and 41 financial ratios, 30 times of holdout experiments are carried out for FDP respectively one year, two years, and three years in advance. In terms of experimental results, AdaBoost ensemble with SAT outperforms AdaBoost ensemble with DT, single DT classifier and single SVM classifier. As a conclusion, the choice of weak learner is crucial to the performance of AdaBoost ensemble, and AdaBoost ensemble with SAT is more suitable for FDP of Chinese listed companies. [Copyright &y& Elsevier]

Abstract: Cantonese is an important dialect in some regions of Southern China. Local online users often represent their opinions and experiences on the web with written Cantonese. Although the information in those reviews is valuable to potential consumers and sellers, the huge amount of web reviews make it difficult to give an unbiased evaluation to a product and the Cantonese reviews are unintelligible for Mandarin Chinese speakers. In this paper, standard machine learning techniques naive Bayes and SVM are incorporated into the domain of online Cantonese-written restaurant reviews to automatically classify user reviews as positive or negative. The effects of feature presentations and feature sizes on classification performance are discussed. We find that accuracy is influenced by interaction between the classification models and the feature options. The naive Bayes classifier achieves as well as or better accuracy than SVM. Character-based bigrams are proved better features than unigrams and trigrams in capturing Cantonese sentiment orientation. [Copyright &y& Elsevier]

Abstract: To maintain the balance of byproduct gas holder is an important task in optimal scheduling of byproduct energy in steel industry. However, this is often influenced by many factors and is difficult to obtain a precise mechanism model for analysis. In this paper, an optimal method for prediction and adjustment on byproduct gas holder is proposed. Considering the different operation styles of gasholders, both single and multiple gasholders level prediction models are established by machine learning methodology. And, a hybrid parameter optimization algorithm is developed to optimize the model for high prediction accuracy. Then, based on the predicted gasholder level, the optimal adjustment amount is calculated by a novel reasoning method to sustain the gasholder within safety zone. This method has been verified in the Energy Center of Baosteel, China. The results demonstrate that the proposed approach can precisely predict and adjust gasholders and provide a remarkable guidance for reasonable scheduling of byproduct gases. [ABSTRACT FROM AUTHOR]

Abstract: In recent years, more and more people, especially young people, begin to use credit card with the changing of consumption concept in China so that the business on credit cards is growing fast. Therefore, it is significative that some effective tools such as credit-scoring models are created to help those decision makers engaged in credit cards. A novel credit-scoring model, called vertical bagging decision trees model (abbreviated to VBDTM), is proposed for the purpose in this paper. The model is a new bagging method that is different from the traditional bagging. The VBDTM model gets an aggregation of classifiers by means of the combination of predictive attributes. In the VBDTM model, all train samples and just parts of attributes take part in learning of every classifier. By contrast, classifiers are trained with the sample subsets in the traditional bagging method and every classifier has the same attributes. The VBDTM has been tested by two credit databases from the UCI Machine Learning Repository, and the analysis results show that the performance of the method proposed by us is outstanding on the prediction accuracy. [ABSTRACT FROM AUTHOR]