Search results

This paper aims to compare the forecasting performance of different models with and without big data predictors from search engines and social media.

Using daily tourist arrival data to Mount Longhu, China in 2018 and 2019, the authors estimated ARMA, ARMAX, Markov-switching auto-regression (MSAR), lasso model, elastic net model and post-lasso and post-elastic net models to conduct one- to seven-days-ahead forecasting. Search engine data and social media data from WeChat, Douyin and Weibo were incorporated to improve forecasting accuracy.

Results show that search engine data can substantially reduce forecasting error, whereas social media data has very limited value. Compared to the ARMAX/MSAR model without big data predictors, the corresponding post-lasso model reduced forecasting error by 39.29% based on mean square percentage error, 33.95% based on root mean square percentage error, 46.96% based on root mean squared error and 45.67% based on mean absolute scaled error.

Results highlight the importance of incorporating big data predictors into daily demand forecasting for tourism attractions.

This study represents a pioneering attempt to apply the regularized regression (e.g. lasso model and elastic net) in tourism forecasting and to explore various daily big data indicators across platforms as predictors.

The purpose of this paper is to demonstrate the applicability of swarm and evolutionary techniques for regularized machine learning. Generally, by defining a proper penalty function, regularization laws are embedded into the structure of common least square solutions to increase the numerical stability, sparsity, accuracy and robustness of regression weights. Several regularization techniques have been proposed so far which have their own advantages and disadvantages. Several efforts have been made to find fast and accurate deterministic solvers to handle those regularization techniques. However, the proposed numerical and deterministic approaches need certain knowledge of mathematical programming, and also do not guarantee the global optimality of the obtained solution. In this research, the authors propose the use of constraint swarm and evolutionary techniques to cope with demanding requirements of regularized extreme learning machine (ELM).

To implement the required tools for comparative numerical study, three steps are taken. The considered algorithms contain both classical and swarm and evolutionary approaches. For the classical regularization techniques, Lasso regularization, Tikhonov regularization, cascade Lasso-Tikhonov regularization, and elastic net are considered. For swarm and evolutionary-based regularization, an efficient constraint handling technique known as self-adaptive penalty function constraint handling is considered, and its algorithmic structure is modified so that it can efficiently perform the regularized learning. Several well-known metaheuristics are considered to check the generalization capability of the proposed scheme. To test the efficacy of the proposed constraint evolutionary-based regularization technique, a wide range of regression problems are used. Besides, the proposed framework is applied to a real-life identification problem, i.e. identifying the dominant factors affecting the hydrocarbon emissions of an automotive engine, for further assurance on the performance of the proposed scheme.

Through extensive numerical study, it is observed that the proposed scheme can be easily used for regularized machine learning. It is indicated that by defining a proper objective function and considering an appropriate penalty function, near global optimum values of regressors can be easily obtained. The results attest the high potentials of swarm and evolutionary techniques for fast, accurate and robust regularized machine learning.

The originality of the research paper lies behind the use of a novel constraint metaheuristic computing scheme which can be used for effective regularized optimally pruned extreme learning machine (OP-ELM). The self-adaption of the proposed method alleviates the user from the knowledge of the underlying system, and also increases the degree of the automation of OP-ELM. Besides, by using different types of metaheuristics, it is demonstrated that the proposed methodology is a general flexible scheme, and can be combined with different types of swarm and evolutionary-based optimization techniques to form a regularized machine learning approach.

Demand forecasts are a key component of planning efforts and are crucial for managing core operations. This study aims to evaluate the use of several machine learning (ML) algorithms to forecast demand for residential construction in Jordan.

The identification and selection of variables and ML algorithms that are related to the demand for residential construction are indicated using a literature review. Feature selection was done by using a stepwise backward elimination. The developed algorithm’s accuracy has been demonstrated by comparing the ML predictions with real residual values and compared based on the coefficient of determination.

Nine economic indicators were selected to develop the demand models. Elastic-Net showed the highest accuracy of (0.838) versus artificial neural networkwith an accuracy of (0.727), followed by Eureqa with an accuracy of (0.715) and the Extra Trees with an accuracy of (0.703). According to the results of the best-performing model forecast, Jordan’s 2023 first-quarter demand for residential construction is anticipated to rise by 11.5% from the same quarter of the year 2022.

The results of this study extend to the existing body of knowledge through the identification of the most influential variables in the Jordanian residential construction industry. In addition, the models developed will enable users in the fields of construction engineering to make reliable demand forecasts while also assisting in effective financial decision-making.

Survival (default) data are frequently encountered in financial (especially credit risk), medical, educational, and other fields, where the “default” can be interpreted as the failure to fulfill debt payments of a specific company or the death of a patient in a medical study or the inability to pass some educational tests.

This paper introduces the basic ideas of Cox's original proportional model for the hazard rates and extends the model within a general framework of statistical data mining procedures. By employing regularization, basis expansion, boosting, bagging, Markov chain Monte Carlo (MCMC) and many other tools, we effectively calibrate a large and flexible class of proportional hazard models.

The proposed methods have important applications in the setting of credit risk. For example, the model for the default correlation through regularization can be used to price credit basket products, and the frailty factor models can explain the contagion effects in the defaults of multiple firms in the credit market.

The purpose of this study is to estimate aerodynamic parameters using regularized regression-based methods.

Regularized regression methods used are LASSO, ridge and elastic net.

A viable option of aerodynamic parameter estimation from regularized regression-based methods is found.

Efficacy of the methods is examined on flight test data.

This study provides regularized regression-based methods for aerodynamic parameter estimation from the flight test data.

In short-term forecasting of day-ahead electricity prices, incorporating intraday dependencies is vital for accurate predictions. However, it quickly leads to dimensionality problems, i.e. ill-defined models with too many parameters, which require an adequate remedy. This study addresses this issue.

In an application for the German/Austrian market, this study derives variable importance scores from a random forest algorithm, feeds the identified variables into a support vector machine and compares the resulting forecasting technique to other approaches (such as dynamic factor models, penalized regressions or Bayesian shrinkage) that are commonly used to resolve dimensionality problems.

This study develops full importance profiles stating which hours of which past days have the highest predictive power for specific hours in the future. Using the profile information in the forecasting setup leads to very promising results compared to the alternatives. Furthermore, the importance profiles provide a possible explanation why some forecasting methods are more accurate for certain hours of the day than others. They also help to explain why simple forecast combination schemes tend to outperform the full battery of models considered in the comprehensive comparative study.

With the information contained in the variable importance scores and the results of the extensive model comparison, this study essentially provides guidelines for variable and model selection in future electricity market research.

Warehouses are large emitters of greenhouse gases and their impact on climate change is under increasing focus. The purpose of this paper is to investigate the barriers that inhibit the adoption of low-carbon warehousing in Asia-Pacific and their links to carbon abatement performance.

An exploratory conceptual model was first developed from a literature review of the general barriers to sustainable supply chain practices and hence potentially in low-carbon warehousing. A large contract logistics services provider in the Asia-Pacific served as the subject of a case study. The perceived barriers to low-carbon warehousing were derived from an internal survey of respondents from the case company and regressed against carbon abatement outcomes at that organization’s operations across the region.

Results show that the case company reduced carbon emissions by 36 percent on a revenue-normalized basis between 2008 and 2014, but with relatively lower success in emerging markets vs mature markets. An Elastic Net regression analysis confirms that technology and government-related factors are the most important barriers in the case company’s efforts to “decarbonize” its local warehousing operations. However, results suggest that the customer-related barrier, which is highly correlated with the government barrier, is in part driven by the latter.

This case study is based on a single multinational company in Asia-Pacific, but nonetheless serves as an impetus for more cross-sectional studies to form an industry-wide view.

An extended stewardship framework based on the natural resource-based view has been proposed, in which logistics services providers take on a proactive boundary-spanning role to lower the external barriers to low-carbon warehousing.

This paper aims to investigate the impact of climate change news on the dynamics of US stock indices.

The empirical basis of the study was 3,209 news articles. Sentiment analysis was performed by a pre-trained bidirectional FinBERT neural network. Thematic modeling is based on the neural network, BERTopic.

The results show that news sentiment can influence the dynamics of stock indices. In addition, five main news topics (finance and politics natural disasters and consequences industrial sector and Innovations activism and culture coronavirus pandemic) were identified, which showed a significant impact on the financial market.

First, we extend the theoretical concepts. This study applies signaling theory and overreaction theory to the US stock market in the context of climate change. Second, in addition to the news sentiment, the impact of major news topics on US stock market returns is examined. Third, we examine the impact of sentimental and thematic news variables on US stock market indicators of economic sectors. Previous works reveal the impact of climate change news on specific sectors of the economy. This paper includes stock indices of the economic sectors most related to the topic of climate change. Fourth, the research methodology consists of modern algorithms. An advanced textual analysis method for sentiment classification is applied: a pre-trained bidirectional FinBERT neural network. Modern thematic modeling is carried out using a model based on the neural network, BERTopic. The most extensive topics are “finance and politics of climate change” and “natural disasters and consequences.”

This paper aims to use a data-driven approach towards optimizing construction operations. To this extent, it presents a machine learning (ML)-aided optimization approach, wherein the construction cost is predicted as a function of time, resources and environmental impact, which is further used as a surrogate model for cost optimization.

Taking a dataset from literature, the paper has applied various ML algorithms, namely, simple and regularized linear regression, random forest, gradient boosted trees, neural network and Gaussian process regression (GPR) to predict the construction cost as a function of time, resources and environmental impact. Further, the trained models were used to optimize the construction cost applying single-objective (with and without constraints) and multi-objective optimizations, employing Bayesian optimization, particle swarm optimization (PSO) and non-dominated sorted genetic algorithm.

The results presented in the paper demonstrate that the ensemble methods, such as gradient boosted trees, exhibit the best performance for construction cost prediction. Further, it shows that multi-objective optimization can be used to develop a Pareto front for two competing variables, such as cost and environmental impact, which directly allows a practitioner to make a rational decision.

Note that the sequential nature of events which dictates the scheduling is not considered in the present work. This aspect could be incorporated in the future to develop a robust scheme that can optimize the scheduling dynamically.

The paper demonstrates that a ML approach coupled with optimization could enable the development of an efficient and economic strategy to plan the construction operations.

This study aims to develop a novel approach for predicting default risk in bancassurance, which plays a crucial role in the relationship between interest rates in banks and premium rates in insurance companies. The proposed method aims to improve default risk predictions and assist with client segmentation in the banking system.

This research introduces the group method of data handling (GMDH) technique and a diversified classifier ensemble based on GMDH (dce-GMDH) for predicting default risk. The data set comprises information from 30,000 credit card clients of a large bank in Taiwan, with the output variable being a dummy variable distinguishing between default risk (0) and non-default risk (1), whereas the input variables comprise 23 distinct features characterizing each customer.

The results of this study show promising outcomes, highlighting the usefulness of the proposed technique for bancassurance and client segmentation. Remarkably, the dce-GMDH model consistently outperforms the conventional GMDH model, demonstrating its superiority in predicting default risk based on various error criteria.

This study presents a unique approach to predicting default risk in bancassurance by using the GMDH and dce-GMDH neural network models. The proposed method offers a valuable contribution to the field by showcasing improved accuracy and enhanced applicability within the banking sector, offering valuable insights and potential avenues for further exploration.