Search

Tourism managers and practitioners rely on accurate demand forecasting and well-informed management guidance. Given the pandemic's consequences on tourism, future analysis in the during-epidemic era is urgently needed. This study aims to achieve three goals combining the utilization of decomposition algorithms and deep learning models: 1) to investigate the changes in tourism demand according to seasonal fluctuations of various frequencies, 2) to improve modelling accuracy in tourism demand forecasting during non-crisis periods and in the peri-COVID-19 era, and 3) to analyze tourism demand evolution in the peri-Covid-19 era. The volume of domestic tourism in Hawaii is used as sample data for demonstration and validation. The empirical findings demonstrate that the framework provided in this study has excellent interpretability and forecasting accuracy, surpasses all benchmark models in terms of error calculation and statistical tests and can provide further insights into peri-Covid-19 demand analysis and management. [ABSTRACT FROM AUTHOR]

The security of credit card fraud detection (CCFD) models based on machine learning is important but rarely considered in the existing research. To this end, we propose a black-box attack-based security evaluation framework for CCFD models. Under this framework, the semisupervised learning technique and transfer-based black-box attack are combined to construct two versions of a semisupervised transfer black-box attack algorithm. Moreover, we introduce a new nonlinear optimization model to generate the adversarial examples against CCFD models and a security evaluation index to quantitatively evaluate the security of them. Computing experiments on two real data sets demonstrate that, facing the adversarial examples generated by the proposed attack algorithms, all six supervised models considered largely lose their ability to identify the fraudulent transactions, whereas the two unsupervised models are less affected. This indicates that the CCFD models based on supervised machine learning may possess substantial security risks. In addition, the evaluation results for the security of the models generate important managerial implications that help banks reasonably evaluate and enhance the model security. History: Accepted by Ram Ramesh, Area Editor for Data Science & Machine Learning. Funding: This work was supported in part by the National Natural Science Foundation of China [Grants 72171160 and 71988101], Key Program of National Natural Science Foundation of China and Quebec Research Foundation (NSFC-FRQ) Joint Project [Grant 7191101304], Key Program of NSFC-FRQSC Joint Project [Grant 72061127002], Excellent Youth Foundation of Sichuan Province [Grant 2020JDJQ0021], and National Leading Talent Cultivation Project of Sichuan University [Grant SKSYL2021-03]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information (https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2023.1297) as well as from the IJOC GitHub software repository (https://github.com/INFORMSJoC/2021.0076) at (http://dx.doi.org/10.5281/zenodo.7631457). [ABSTRACT FROM AUTHOR]

Effective and timely forecasting of daily tourism volume is an important topic for tourism practitioners and researchers, which can reduce waste and promote the sustainable development of tourism. Several studies are based on the decomposition-ensemble model to forecast the time series of high volatility in tourism volume, but ignore different forecasting methods suitable for different subseries. This study provides an adaptive decomposition-ensemble hybrid forecasting approach. Firstly, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is used to effectively decompose the original time series into multiple relatively easy subseries, which reduces the complexity of the data. Secondly, sample entropy calculates the complexity of a sequence, and then adopts the elbow rule to adaptively divide them into different complex sets. Finally, multi-kernel extreme learning machine (KELM) models are used to forecast the components of different sets and integrate them. This hybrid approach makes full use of the advantages of different models, which enables effective use of data. The empirical results demonstrate that the approach can both produce results that are close to the actual values and be utilized as a strategy for forecasting daily tourism volume. [ABSTRACT FROM AUTHOR]

A reliable and efficient forecasting system can be used to warn the general public against the increasing PM2.5 concentration. This paper proposes a novel AdaBoost‐ensemble technique based on a hybrid data preprocessing‐analysis strategy, with the following contributions: (i) a new decomposition strategy is proposed based on the hybrid data preprocessing‐analysis strategy, which combines the merits of two popular decomposition algorithms and has been proven to be a promising decomposition strategy; (ii) the long short‐term memory (LSTM), as a powerful deep learning forecasting algorithm, is applied to individually forecast the decomposed components, which can effectively capture the long‐short patterns of complex time series; and (iii) a novel AdaBoost‐LSTM ensemble technique is then developed to integrate the individual forecasting results into the final forecasting results, which provides significant improvement to the forecasting performance. To evaluate the proposed model, a comprehensive and scientific assessment system with several evaluation criteria, comparison models, and experiments is designed. The experimental results indicate that our developed hybrid model considerably surpasses the compared models in terms of forecasting precision and statistical testing and that its excellent forecasting performance can guide in developing effective control measures to decrease environmental contamination and prevent the health issues caused by a high PM2.5 concentration. [ABSTRACT FROM AUTHOR]

The availability of tourism-related big data increases the potential to improve the accuracy of tourism demand forecasting but presents significant challenges for forecasting, including curse of dimensionality and high model complexity. A novel bagging-based multivariate ensemble deep learning approach integrating stacked autoencoder and kernel-based extreme learning machine (B-SAKE) is proposed to address these challenges in this study. By using historical tourist arrival data, economic variable data, and search intensity index (SII) data, we forecast tourist arrivals in Beijing from four countries. The consistent results of multiple schemes suggest that our proposed B-SAKE approach outperforms the benchmark models in terms of level accuracy, directional accuracy, and even statistical significance. Both bagging and stacked autoencoder can effectively alleviate the challenges brought by tourism big data and improve the forecasting performance of the models. The ensemble deep learning model we propose contributes to tourism demand forecasting literature and benefits relevant government officials and tourism practitioners. [ABSTRACT FROM AUTHOR]

Decomposition methods are extensively used for processing the complex patterns of tourism demand data. Given tourism demand data's intrinsic complexity, it is critical to theoretically understand how different decomposition methods provide solutions. However, a comprehensive comparison of decomposition methods in tourism demand forecasting is still lacking. Hence, this study systematically investigates the forecasting performance of decomposition methods in tourism demand. Nine popular decomposition methods and six forecasting methods are employed, and their forecasting performance is compared. With Hong Kong visitor arrivals from eight major sources as a sample, three main conclusions are obtained from empirical results. First, all the decomposition methods generally outperform benchmark at all horizons, in both the level and directional forecasting. Second, decomposition methods can be divided into four categories based on forecasting accuracy. Finally, variational mode decomposition method is consistently superior to other eight decomposition methods and can provide the best forecasts in all cases. [ABSTRACT FROM AUTHOR]

In recent years, Bitcoin has received substantial attention as potentially high-earning investment. However, its volatile price movement exhibits great financial risks. Therefore, how to accurately predict and capture changing trends in the Bitcoin market is of substantial importance to investors and policy makers. However, empirical works in the Bitcoin forecasting and trading support systems are at an early stage. To fill this void, this study proposes a novel data decomposition-based hybrid bidirectional deep-learning model in forecasting the daily price change in the Bitcoin market and conducting algorithmic trading on the market. Two primary steps are involved in our methodology framework, namely, data decomposition for inner factors extraction and bidirectional deep learning for forecasting the Bitcoin price. Results demonstrate that the proposed model outperforms other benchmark models, including econometric models, machine-learning models, and deep-learning models. Furthermore, the proposed model achieved higher investment returns than all benchmark models and the buy-and-hold strategy in a trading simulation. The robustness of the model is verified through multiple forecasting periods and testing intervals. [ABSTRACT FROM AUTHOR]

Purpose: This study aims to explore the role of equity investment in knowledge-driven business model innovation (BMI) in context of open modes according to the evidence from China's primary market. Design/methodology/approach: Based on the database of China's private market and data set of news clouds, the statistic approach is applied to explore and explain whether equity investment promotes knowledge-driven BMI. Machine learning method is also used to prove and predict the performance of such open innovation. Findings: The results of logistic regression show that explanatory variables are significant, providing evidence that knowledge management (KM) promotes BMI through equity investment. By further using back propagation neural network, the classification learning algorithm estimates the possibility of BMI, which can be regarded as a score to quantify the performance of knowledge-driven BMI Research limitations/implications: The quality of secondhand big data is not very ideal, and future empirical studies should use first-hand survey data. Practical implications: This study provides new insights into the link between KM and BMI by highlighting the important roles of external investments in open modes. Social implications: From the perspective of investment, the findings of this study suggest the importance for stakeholders to share knowledge and strategies for entrepreneurs to manage innovation. Originality/value: The concepts and indicators related to business models are difficult to quantify currently, while this study provides feasible and practical methods to estimate knowledge-driven BMI with secondhand data from the primary market. The mechanism of knowledge and innovation bridged by the experience from investors is introduced and analyzed. [ABSTRACT FROM AUTHOR]

A clustering-based nonlinear ensemble (CNE) learning approach is proposed in this paper to forecast exchange rates. In the proposed CNE learning approach: 1) a self-organizing map neural network is introduced to cluster the in-sample component forecasts; 2) kernel-based extreme learning machine is employed to calculate the in-sample ensemble weights for each cluster; and 3) the corresponding clusters’ in-sample ensemble weights are used for out-of-sample component forecasts to obtain the ensemble forecasts. To illustrate and verify the effectiveness of our proposed model, we test its directional and level forecasting accuracy using four major exchange rates. The out-of-sample forecasting performance results show that the proposed CNE learning approach consistently outperforms the component models and other ensemble learning approaches in terms of the directional forecasting accuracy and the level forecasting accuracy. [ABSTRACT FROM AUTHOR]

Abstract Previous studies have shown that online data, such as search engine queries, is a new source of data that can be used to forecast tourism demand. In this study, we propose a forecasting framework that uses machine learning and internet search indexes to forecast tourist arrivals for popular destinations in China and compared its forecasting performance to the search results generated by Google and Baidu, respectively. This study verifies the Granger causality and co-integration relationship between internet search index and tourist arrivals of Beijing. Our experimental results suggest that compared with benchmark models, the proposed kernel extreme learning machine (KELM) models, which integrate tourist volume series with Baidu Index and Google Index, can improve the forecasting performance significantly in terms of both forecasting accuracy and robustness analysis. Highlights • We propose kernel extreme learning machine with different kernel functions to accurately forecast tourist arrivals. • Co-integration and granger causality relationship between search engine query data and tourist arrivals are verified. • Baidu index and Google trends data are simultaneously regarded as exogenous variables to forecast Beijing tourist arrivals. • Our proposed approach significantly improves the forecasting performance better than other benchmarks used in this study. [ABSTRACT FROM AUTHOR]

A decomposition-clustering-ensemble (DCE) learning approach is proposed for solar radiation forecasting in this paper. In the proposed DCE learning approach, (1) ensemble empirical mode decomposition (EEMD) is used to decompose the original solar radiation data into several intrinsic mode functions (IMFs) and a residual component; (2) least square support vector regression (LSSVR) is performed to forecast IMFs and residual component respectively with parameters optimized by gravitational search algorithm (GSA); (3) Kmeans method is adopted to cluster all component forecasting results; (4) another GSA-LSSVR method is applied to ensemble the component forecasts of each cluster and the final forecasting results are obtained by means of corresponding cluster’s ensemble weights. To verify the performance of the proposed DCE learning approach, solar radiation data in Beijing is introduced for empirical analysis. The results of out-of-sample forecasting power show that the DCE learning approach produces smaller NRMSE, MAPE and better directional forecasts than all other benchmark models, reaching up to accuracy rate of 2.96%, 2.83% and 88.24% respectively in the one-day-ahead forecasting. This indicates that the proposed DCE learning approach is a relatively promising framework for forecasting solar radiation by means of level accuracy, directional accuracy and robustness. [ABSTRACT FROM AUTHOR]

Customer churn prediction is one of the key steps to maximize the value of customers for an enterprise. It is difficult to get satisfactory prediction effect by traditional models constructed on the assumption that the training and test data are subject to the same distribution, because the customers usually come from different districts and may be subject to different distributions in reality. This study proposes a feature-selection-based dynamic transfer ensemble (FSDTE) model that aims to introduce transfer learning theory for utilizing the customer data in both the target and related source domains. The model mainly conducts a two-layer feature selection. In the first layer, an initial feature subset is selected by GMDH-type neural network only in the target domain. In the second layer, several appropriate patterns from the source domain to target training set are selected, and some features with higher mutual information between them and the class variable are combined with the initial subset to construct a new feature subset. The selection in the second layer is repeated several times to generate a series of new feature subsets, and then, we train a base classifier in each one. Finally, a best base classifier is selected dynamically for each test pattern. The experimental results in two customer churn prediction datasets show that FSDTE can achieve better performance compared with the traditional churn prediction strategies, as well as three existing transfer learning strategies. [ABSTRACT FROM AUTHOR]

Abstract: In frontier analysis, most of nonparametric approaches produce a full frontier that envelopes all observations. Its sensitivity to extreme values and outliers can be overcome by , which is defined as the of the output conditional on a given input. The can be regarded as the benchmark output whether a specified firm achieves top efficiency. This paper proposes a nonparametric smooth multivariate estimation for based on shape-restricted kernel quantile regression. This method explicitly appends the classical kernel quantile regression with two shape restrictions: nondecreasing and concave, which are necessary conditions for production functions. Its training is a semi-infinite programming and can be discretized to a semidefinite programming problem, which is computationally tractable. Theoretical analysis shows that the rate of exceedance in the samples will converge to as the size of training data increases. Experimental results on two toy data sets clearly show that this exploitation of these prior shape knowledge can greatly improve learning performance. Experimental results on a data set from the NBER-CES Manufacturing Industry Database clearly show that the shaped restricted kernel quantile regression can achieve better out-of-sample performance than those of two benchmark methods. [Copyright &y& Elsevier]

After more than ten years of exponential development, the growth rate of cruise tourist in China is slowing down. There is increasingly financial risk of investing in homeports, cruise ships and promotional activities. Therefore, forecasting Chinese cruise tourism demand is a prerequisite for investment decision-making and planning. In order to enhance forecasting performance, a least squares support vector regression model with gravitational search algorithm (LSSVR-GSA) is proposed for forecasting cruise tourism demand with big data, which are search query data (SQD) from Baidu and economic indexes. In the proposed model, hyper-parameters of the LSSVR model are optimized with GSA. By comparing these models with various settings, we find that LSSVR-GSA with selected mobile keywords and economic indexes can achieve the highest forecasting performance. The results indicate the proposed framework of the methodology is effective and big data can be helpful predictors for forecasting Chinese cruise tourism demand. [ABSTRACT FROM AUTHOR]

• A two stage-based feature selection approach for forecasting is proposed. • The approach relies on machine learning model combined with feature selection method. • With different forecasting horizons and datasets, results are predominant. • The study confirms the value of exploring the more effective keywords subset. • The results provide some implications for forecasting using multisource data. Search engine data have been widely used and shown to be useful in tourism demand forecasting. However, considering of the vast amounts of search keywords, how to better capture the tourists' attention and explore the most predictive keyword combination remain unsolved. In this study, a two-stage feature selection-based methodology is proposed to address this question. Specifically, i.e., single feature selection method comparison for selecting a relative effective way to reduce the data dimension and ensure the quality of the initial subset, genetic algorithm in the second stage for obtaining feature subset better suitable for forecasting model with stronger predictive power. Experimental results indicate that the two-stage feature selection method outperforms all the considered benchmarks. [ABSTRACT FROM AUTHOR]

• Multi-step ahead demand forecasting is an important and cutting-edge research topic. • An effective forecasting approach incorporating privileged information is proposed. • The new paradigm (termed learning using privileged information (LUPI)) is imployed. • LUPI can efficiently grasp and model nonlinear characteristics of tourism data. • The empirical results verify its superiority and robustness with different samples. Accurate tourism demand forecasting can provide effective guidance for government management and tourism planning. Specifically, multi-step ahead tourism demand forecasting is of great relevance in guiding managers to develop strategies and assisting operators in business planning and is therefore of great interest to researchers and practitioners. However, it is usually difficult to obtain satisfactory accuracy in views of sophisticated data characteristics. This study proposes an improved machine learning paradigm, introducing valuable additional information into the training phase, which is not available for forecasting in the testing phase. Taking Hawaii (Daily and Weekly) and Macau tourist arrivals as the samples, the empirical evidence indicates that the proposed approach can significantly enhance the multi-step ahead forecasting performance from the view of both error calculation and statistical test. In particular, the paradigm's robustness is also demonstrated in the comparison of sliding window predictions with models of variants. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, a four-stage support vector machine (SVM) based multiagent ensemble learning approach is proposed for credit risk evaluation. In the first stage, the initial dataset is divided into two independent subsets: training subset (in-sample data) and testing subset (out-of-sample data) for training and verification purposes. In the second stage, different SVM learning paradigms with much dissimilarity are constructed as intelligent agents for credit risk evaluation. In the third stage, multiple individual SVM agents are trained using training subsets and the corresponding evaluation results are also obtained. In the final stage, all individual results produced by multiple SVM agents in the previous stage are aggregated into an ensemble result. In particular, the impact of the diversity of individual intelligent agents on the generalization performance of the SVM-based multiagent ensemble learning system is examined and analyzed. For illustration, one corporate credit card application approval dataset is used to verify the effectiveness of the SVM-based multiagent ensemble learning system. [Copyright &y& Elsevier]

To mitigate the impact of market uncertainty on trading investments, this paper proposes a forecasting and investing framework for crude oil market by integrating interval models and machine learning models. Firstly, natural language processing technique is employed to analyze text information from social and news media, enabling the capture of market and societal sentiment. Subsequently, deep learning models are integrated to combine sentiment data with other economic variables for more accurate predictions of crude oil prices. Furthermore, this paper introduces a trading strategy with interval constraints based on interval prediction models to reduce trading risk arising from the uncertainty of point forecasts in investments. Through trading simulations, it is discovered that employing the interval constrained strategy is more effective in reducing trading risk and enhancing investment returns compared to point-based trading strategies. This interval-based strategy offers a novel approach to mitigating investment risk in the crude oil market. • A novel prediction framework is proposed to integrate text data and interval data. • Combining point-valued and interval-valued deep learning models. • An interval-based trading strategy is developed. • The proposed trading strategy can reduce risk while improving investment returns. [ABSTRACT FROM AUTHOR]

With rapid development of financial services and products, credit risk assessment has recently gained considerable attention in the field of financial risk management. In this paper, an improved credit risk assessment approach is presented. Based on the credit data from China Banking Regulatory Commission (CBRC), a multi-dimensional and multi-level credit risk indicator system is constructed. In particular, we present an improved sequential minimal optimization (SMO) learning algorithm, named four-variable SMO (FV-SMO), for credit risk classification model. At each iteration, it jointly selects four variables into the working set and an theorem is proposed to guarantee the analytical solution of sub-problem. The assessment is made on China credit dataset and two benchmark credit datasets from UCI database and CD-ROM database. Experimental results demonstrate FV-SMO is competitive in saving the computational cost and outperforms other five state-of-the-art classification methods in credit risk assessment accuracy. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) techniques have substantially changed the research paradigm in the field of air quality forecasting due to their powerful performance. Considering the improvement in the availability of air quality data and the rapid proliferation of AI techniques, it is necessary to comprehensively and quantitatively review the development of air quality forecasting with AI techniques during the last two decades (2000–2019) by scientometric and content analysis. First, an overview of the relevant countries, institutions, authors, journals, and papers is presented. Then, the research hotspots and frontier evolution are explored by adopting reference co-citation analysis and keyword co-occurrence analysis. Furthermore, this study conducts a content analysis to investigate current topical interests to identify research gaps and propose future research directions. The analytical framework and the findings provide helpful insights into the prospects in air quality forecasting with AI techniques. • Air quality forecasting with AI is investigated deeply and comprehensively. • A top-down review integrating scientometric and content analysis is adopted. • Various statistics and visualizations of this research field are provided. • The research hotspots and frontier evolution in this research field are explored. [ABSTRACT FROM AUTHOR]

Current electricity price forecasting models rely on only simple hybridizations of data preprocessing and optimization methods while ignoring the significance of adaptive data preprocessing and effective optimization and selection strategies to obtain optimal models that improve the forecasting performance. To solve these problems, this study develops an improved electricity price forecasting model that offers the advantages of adaptive data preprocessing, advanced optimization method, kernel-based model, and optimal model selection strategy. Specifically, the adaptive parameter-based variational mode decomposition technology is proposed to provide desirable data preprocessing results, and a leave-one-out optimization strategy based on the chaotic sine cosine algorithm is proposed and applied to develop optimal kernel-based extreme learning machine models. In addition, a newly proposed optimal model selection strategy is applied to determine the developed model that provides the most desirable forecasting result. Numerical results show that the developed model's performance metrics were best, and the average values of mean absolute error, root mean square error, mean absolute percentage error, index of agreement, and Theil's inequality coefficient in four datasets are 0.5121, 0.7607, 0.5722%, 0.9997 and 0.0041, respectively, which imply that the developed model is a promising, applicable and effective electricity price forecasting technique in the real electricity market. • Optimal model selection strategy is proposed for improving forecasting performance. • Leave-one-out optimization strategy is proposed for developing an optimal model. • The significance of adaptive data preprocessing is considered in this study. • The developed model exhibits better performance for modeling electricity price. [ABSTRACT FROM AUTHOR]