Search

Tourism volume forecasting is the hot topic in tourism management, and deep learning techniques as the promising tool are becoming popular for capturing the characteristics of tourism volume data, which is reflected in two aspects: data dimension reduction (i.e., stacked autoencoders [SAE]) and model forecasting (i.e., bi‐directional gated recurrent unit neural network [Bi‐GRU]). With Hong Kong inbound arrivals as a case, this study has empirically verified that deep learning techniques can improve forecasting accuracy. Furthermore, the proposed approach (i.e., SAE‐Bi‐GRU) is significantly superior to benchmark models (i.e., PCA‐Bi‐GRU with Baidu index and Google trends). [ABSTRACT FROM AUTHOR]

With the orderly advancement of China Energy Development Strategic Action Plan, clean energy has become a major trend in the energy market. As a major industry of clean energy, natural gas industry plans to consume at least 10% of the total primary energy by 2020. The energy structure will be improved in an orderly manner to achieve the goal of energy conservation, consumption reduction, and emission reduction. To achieve energy saving and emission reduction, and using clean energy effectively, accurate prediction of natural gas consumption is of great importance. Because of the many influencing factors affecting natural gas demand, this paper first utilizes STRIPAT to analyze the factors affecting natural gas consumption and then uses a deep learning ensemble approach to analyze and predict China's natural gas consumption. One is an advanced deep neural network model named gated recurrent unit model which is used to model the nonlinear and complex relationships of natural gas consumption with its factors. The other is a powerful ensemble method named bootstrap aggregation which generates multiple data sets for training a set of base models. Our approach combines the advantages of these two technologies to forecast the demand for China's natural gas market. In empirical research, our method has been tested by some competitive methods and has shown superiority. [ABSTRACT FROM AUTHOR]

Forecasting air passenger flows is receiving increasing attention, especially due to its intrinsic difficulties and wide applications. Total passengers are used as a proxy for air transport demand. However, the time series of air passenger flows usually has complicated behavior with high volatility and irregularity. This paper proposes a MIV-based nonlinear vector auto-regression neural network (NVARNN) approach to forecast air passenger flows. In the proposed MIV-NVARNN learning approach, (1) a method of mean impact value (MIV) based on neural network is used for identifying and extracting input variables; (2) NVARNN is firstly proposed to deal with the irregularity and volatility of the time series of air passenger flows. To illustrate and verify the effectiveness of the proposed approach, we tested its directional and level forecasting accuracy using the time series of Beijing International Airport's passenger flows. The results of out-of-sample forecasting performance show that the proposed MIV-NVARNN approach consistently outperforms single models and other hybrid approaches in terms of level forecasting accuracy, directional forecasting accuracy and robustness analysis. • A new hybrid approach is proposed for air passenger flow forecasting. • Two steps are involved: variable selection and forecast modelling. • Nonlinear vector auto-regression neural network is firstly developed to forecast air passenger flow. • Empirical results statistically verify the forecasting performance of our new hybrid approach. [ABSTRACT FROM AUTHOR]

This paper presents an integrated forecasting model based on the TEI@I methodology for forecasting demand for port logistics services – specifically, port container throughput. The model analyzes port logistics time series data and other information in several steps. In the first step, several econometric models are built to forecast the linear segment of port logistics time series. In the second step, a radial basis function neural network is developed to predict the nonlinear segment of the time series. In the third step, the event-study method and expert system techniques are applied to evaluate the effects of economic and other events that may impact demand for port logistics. In the final step, synthetic forecasting results are obtained, based on the integration of predictions from the above three steps. For an illustration, Hong Kong port's container throughput series is used as a case study. The empirical results show the effectiveness of the TEI@I integrated model for port logistics forecasting. [ABSTRACT FROM PUBLISHER]

For time series, the problem that we often encounter is how to extract the patterns hidden in the real world data for forecasting its future values. A single linear or nonlinear model is inadequate in modeling and forecasting the time series, because most of them usually contain both linear and nonlinear patterns. This study constructs a hybrid forecasting model that combines autoregressive integrated moving average (ARIMA) with Elman artificial neural network (ANN) for short-term forecasting of time series. The proposed approach considers the linear and nonlinear patterns in the real data simultaneously so that it can mine more precise characteristics to describe the time series better. Finally, the forecasting results of the hybrid model are adjusted with the knowledge from text mining and expert system. The empirical results on the container throughput forecast of Tianjin Port show that the forecasts by the hybrid model are superior to those of ARIMA model and Elman network. [ABSTRACT FROM AUTHOR]

In this study, a novel forecasting model based on the Wavelet Neural Network (WNN) is proposed to predict the monthly crude oil spot price. In the proposed model, the OECD industrial petroleum inventory level is used as an independent variable, and the Wavelet Neural Network (WNN) is used to explore the nonlinear relationship between inventories and the price. For verification purposes, the West Texas Intermediate (WTI) crude oil spot price is used for the tested target. Experimental results reveal that the WNN can model the nonlinear relationship between inventories and the price very well. Furthermore, the in-sample and out-of-sample prediction performance also demonstrates that the WNN-based forecasting model can produce more accurate prediction results than other nonlinear and linear models, even when the lengths of the forecast horizon are relatively short or long. [ABSTRACT FROM AUTHOR]

Abstract: A financial crisis is typically a rare kind of an event, but it hurts sustainable economic development when it occurs. This study proposes a multiscale neural network learning paradigm to predict financial crisis events for early-warning purposes. In the proposed multiscale neural network learning paradigm, currency exchange rate, a typical financial indicator that usually reflects economic fluctuations, is first chosen. Then a Hilbert-EMD algorithm is applied to the currency exchange rate series. Using the Hilbert-EMD procedure, some intrinsic mode components (IMCs) of the currency exchange rate series, with different scales, can be obtained. Subsequently, the internal correlation structures of different IMCs are explored by a neural network model. Using the neural network weights, some important IMCs are selected as the final neural network inputs and some unimportant IMCs that are of little use in mapping from inputs to output are discarded. Using these selected IMCs, a neural network learning paradigm is used to predict future financial crisis events, based upon some historical data. For illustration purpose, the proposed multiscale neural network learning paradigm is applied to exchange rate data of two Asian countries to evaluate the state of financial crisis. Experimental results reveal that the proposed multiscale neural network learning paradigm can significantly improve the generalization performance relative to conventional neural networks. [Copyright &y& Elsevier]

Abstract: In financial time series forecasting, the problem that we often encounter is how to increase the prediction accuracy as possible using the financial data with noise. In this study, we discuss the use of supervised neural networks as a meta-learning technique to design a financial time series forecasting system to solve this problem. In this system, some data sampling techniques are first used to generate different training subsets from the original datasets. In terms of these different training subsets, different neural networks with different initial conditions or training algorithms are then trained to formulate different prediction models, i.e., base models. Subsequently, to improve the efficiency of predictions of metamodeling, the principal component analysis (PCA) technique is used as a pruning tool to generate an optimal set of base models. Finally, a neural-network-based nonlinear metamodel can be produced by learning from the selected base models, so as to improve the prediction accuracy. For illustration and verification purposes, the proposed metamodel is conducted on four typical financial time series. Empirical results obtained reveal that the proposed neural-network-based nonlinear metamodeling technique is a very promising approach to financial time series forecasting. [Copyright &y& Elsevier]

Artificial neural networks (ANNs) have been widely applied to finance and economic forecasting as a powerful modeling technique. By reviewing the related literature, we discuss the input variables, type of neural network models, performance comparisons for the prediction of foreign exchange rates, stock market index and economic growth. Economic fundamentals are important in driving exchange rates, stock market index price and economic growth. Most neural network inputs for exchange rate prediction are univariate, while those for stock market index prices and economic growth predictions are multivariate in most cases. There are mixed comparison results of forecasting performance between neural networks and other models. The reasons may be the difference of data, forecasting horizons, types of neural network models and so on. Prediction performance of neural networks can be improved by being integrated with other technologies. Nonlinear combining forecasting by neural networks also provides encouraging results. [ABSTRACT FROM AUTHOR]

Forecasting exchange rates is an important financial problem that is receiving increasing attention especially because of its difficulty and practical applications. Artificial neural networks (ANNs) have been widely used as a promising alternative approach for a forecasting task because of several distinguished features. Research efforts on ANNs for forecasting exchange rates are considerable. In this paper, we attempt to provide a survey of research in this area. Several design factors significantly impact the accuracy of neural network forecasts. These factors include the selection of input variables, preparing data, and network architecture. There is no consensus about the factors. In different cases, various decisions have their own effectiveness. We also describe the integration of ANNs with other methods and report the comparison between performances of ANNs and those of other forecasting methods, and finding mixed results. Finally, the future research directions in this area are discussed. [ABSTRACT FROM AUTHOR]

Abstract: A generic bill-of-materials (GBOM) describes demand for materials and their proportional relations to a family of products. Supply chain constructed from the perspective of the GBOM is able to respond swiftly to market demand and lean production can be achieved by managing the total cost of supply chain effectively. Based on the GBOM, this paper examines the control of production disruption risk related to supply chain and investigates the uncertainty of production in supply chain enterprises for the purpose of achieving optimal profits in supply chain. As the production disruption risk is controlled at a certain level, the selection model of supply chain partners, which is specific and more feasible, can be constructed. A combination of random simulation and neural network is deployed to approximate uncertain function, and genetic algorithm and simulated annealing arithmetic are also used to approximately achieve the optimal scheme of supply chain construction in the context of uncertainty. [Copyright &y& Elsevier]

The forecasting and trading of exchange rates is a prevalent and intricate undertaking within the realm of economics. While prior research has mostly concentrated on enhancing the accuracy of predictions through various methodologies, this study places greater emphasis on providing practical suggestions for effective trading. Hence, we propose a double insurance approach for exchange rate trading. Firstly, this study gathers time series data and textual information from various perspectives and markets. This enables us to generate point value forecasts by leveraging natural language processing and deep learning techniques. Simultaneously, this study employs an innovative interval forecasting method to track the upper and lower limits of daily exchange rate fluctuations. Finally, this study provides a novel trading method aimed at enhancing the possible financial gains associated with exchange rate fluctuations. The proposed methodology is validated through the utilization of exchange rates between the USD and four prominent currencies, namely CNY, JPY, EUR, and GBP. The findings indicate that the inclusion of economic variables and multi-platform sentiment indices enhances the precision of exchange rate prediction. Furthermore, the deep learning model (neural network model) exhibits superior performance compared to benchmark models (i.e. time series models and support vector regression). Furthermore, this study demonstrates that the implementation of the trading strategy with interval constraints significantly improves the profitability of exchange rate trading. [ABSTRACT FROM AUTHOR]

Abstract: In this study, a multistage nonlinear radial basis function (RBF) neural network ensemble forecasting model is proposed for foreign exchanger rates prediction. In the process of ensemble modeling, the first stage produces a great number of single RBF neural network models. In the second stage, a conditional generalized variance (CGV) minimization method is used to choose the appropriate ensemble members. In the final stage, another RBF network is used for neural network ensemble for prediction purpose. For testing purposes, we compare the new ensemble model''s performance with some existing neural network ensemble approaches in terms of four exchange rates series. Experimental results reveal that the predictions using the proposed approach are consistently better than those obtained using the other methods presented in this study in terms of the same measurements. [Copyright &y& Elsevier]

Transportation disruption is the direct result of various accidents in supply chains, which have multiple negative impacts on supply chains and member enterprises. After transportation disruption, market demand becomes highly unpredictable and thus it is necessary for enterprises to better predict market demand and optimize purchase, inventory and production. As such, this article endeavors to design an improved model of grey neural networks to help enterprises better predict market demand after transportation disruption and then the empirical study tests its feasibility. This improved model of grey neural networks exceeds the conventional grey model GM(1,1) with respect to the fact that the raw data tend to show exponential growth and data variation is required to be moderate, demonstrating the good attribute of nonlinear approximation in terms of neural networks, setting up standards for selecting the number of neurons in the input layer of BP neural networks, increasing the fitting degree and prediction accuracy and enhancing the stability and reliability of prediction. It can be applied to sequential data prediction in transportation disruption or mutation, contributing to the prediction of transportation disruption. The forecasting results can provide scientific evidence for demand prediction, inventory management and production of supply chain enterprises. [ABSTRACT FROM AUTHOR]