Search results

Bagging (bootstrap aggregating) is a smoothing method to improve predictive ability under the presence of parameter estimation uncertainty and model uncertainty. In Lee and Yang (2006), we examined how (equal-weighted and BMA-weighted) bagging works for one-step-ahead binary prediction with an asymmetric cost function for time series, where we considered simple cases with particular choices of a linlin tick loss function and an algorithm to estimate a linear quantile regression model. In the present chapter, we examine how bagging predictors work with different aggregating (averaging) schemes, for multi-step forecast horizons, with a general class of tick loss functions, with different estimation algorithms, for nonlinear quantile regression models, and for different data frequencies. Bagging quantile predictors are constructed via (weighted) averaging over predictors trained on bootstrapped training samples, and bagging binary predictors are conducted via (majority) voting on predictors trained on the bootstrapped training samples. We find that median bagging and trimmed-mean bagging can alleviate the problem of extreme predictors from bootstrap samples and have better performance than equally weighted bagging predictors; that bagging works better at longer forecast horizons; that bagging works well with highly nonlinear quantile regression models (e.g., artificial neural network), and with general tick loss functions. We also find that the performance of bagging may be affected by using different quantile estimation algorithms (in small samples, even if the estimation is consistent) and by using different frequencies of time series data.

Incorporating dynamic spatial effects exhibits considerable potential in improving the accuracy of forecasting tourism demands. This study aims to propose an innovative deep learning model for capturing dynamic spatial effects.

A novel deep learning model founded on the transformer architecture, called the spatiotemporal transformer network, is presented. This model has three components: the temporal transformer, spatial transformer and spatiotemporal fusion modules. The dynamic temporal dependencies of each attraction are extracted efficiently by the temporal transformer module. The dynamic spatial correlations between attractions are extracted efficiently by the spatial transformer module. The extracted dynamic temporal and spatial features are fused in a learnable manner in the spatiotemporal fusion module. Convolutional operations are implemented to generate the final forecasts.

The results indicate that the proposed model performs better in forecasting accuracy than some popular benchmark models, demonstrating its significant forecasting performance. Incorporating dynamic spatiotemporal features is an effective strategy for improving forecasting. It can provide an important reference to related studies.

The proposed model leverages high-frequency data to achieve accurate predictions at the micro level by incorporating dynamic spatial effects. Destination managers should fully consider the dynamic spatial effects of attractions when planning and marketing to promote tourism resources.

This study incorporates dynamic spatial effects into tourism demand forecasting models by using a transformer neural network. It advances the development of methodologies in related fields.

纳入动态空间效应在提高旅游需求预测的准确性方面具有相当大的潜力。本研究提出了一种捕捉动态空间效应的创新型深度学习模型。

本研究提出了一种基于变压器架构的新型深度学习模型, 称为时空变压器网络。该模型由三个部分组成：时空转换器、空间转换器和时空融合模块。时空转换器模块可有效提取每个景点的动态时间依赖关系。空间转换器模块可有效提取景点之间的动态空间相关性。提取的动态时间和空间特征在时空融合模块中以可学习的方式进行融合。通过卷积运算生成最终预测结果。

结果表明, 与一些流行的基准模型相比, 所提出的模型在预测准确性方面表现更好, 证明了其显著的预测性能。纳入动态时空特征是改进预测的有效策略。它可为相关研究提供重要参考。

所提出的模型利用高频数据, 通过纳入动态空间效应, 在微观层面上实现了准确预测。旅游目的地管理者在规划和营销推广旅游资源时, 应充分考虑景点的动态空间效应。

本研究通过使用变压器神经网络, 将动态空间效应纳入旅游需求预测模型。它推动了相关领域方法论的发展。

La incorporación de efectos espaciales dinámicos ofrece un considerable potencial para mejorar la precisión de la previsión de la demanda turística. Este estudio propone un modelo innovador de aprendizaje profundo para capturar los efectos espaciales dinámicos.

Se presenta un novedoso modelo de aprendizaje profundo basado en la arquitectura transformadora, denominado red de transformador espaciotemporal. Este modelo tiene tres componentes: el transformador temporal, el transformador espacial y los módulos de fusión espaciotemporal. El módulo transformador temporal extrae de manera eficiente las dependencias temporales dinámicas de cada atracción. El módulo transformador espacial extrae eficientemente las correlaciones espaciales dinámicas entre las atracciones. Las características dinámicas temporales y espaciales extraídas se fusionan de manera que se puede aprender en el módulo de fusión espaciotemporal. Se aplican operaciones convolucionales para generar las previsiones finales.

Los resultados indican que el modelo propuesto obtiene mejores resultados en la precisión de las previsiones que algunos modelos de referencia conocidos, lo que demuestra su importante capacidad de previsión. La incorporación de características espaciotemporales dinámicas supone una estrategia eficaz para mejorar las previsiones. Esto puede proporcionar una referencia importante para estudios afines.

El modelo propuesto aprovecha los datos de alta frecuencia para lograr predicciones precisas a nivel micro incorporando efectos espaciales dinámicos. Los gestores de destinos deberían tener plenamente en cuenta los efectos espaciales dinámicos de las atracciones en la planificación y marketing para la promoción de los recursos turísticos.

Este estudio incorpora efectos espaciales dinámicos a los modelos de previsión de la demanda turística mediante el empleo de una red neuronal transformadora. Supone un avance en el desarrollo de metodologías en campos afines.

Commercial real estate and office rental values, in particular, have long been the focus of research. Several forecasting frameworks for office rental values in multivariate and univariate fashions have been proposed. Recent developments in time series forecasting using machine learning and deep learning methods offer an opportunity to update traditional univariate forecasting frameworks.

With the aim to extend research on univariate rent forecasting a hybrid methodology combining both ARIMA and a neural network model is proposed to exploit the unique strengths of both methods in linear and nonlinear modelling. N-BEATS, a deep learning algorithm that has demonstrated state-of-the-art forecasting performance in major forecasting competitions, are explained. With the ARIMA model, it is jointly applied to the office rental dataset to produce forecasts for four-quarters ahead.

When the approach is applied to a dataset of 21 major European office cities, the results show that the ensemble model can be an effective approach to improve the prediction accuracy achieved by each of the models used separately.

Real estate forecasting is essential for assessing the value of managing portfolios and for evaluating investment strategies. The approach applied in this paper confirms the heterogeneity of real estate markets. The application of mixed modelling via linear and nonlinear methods decreases the uncertainty of abrupt changes in rents.

To the best of the authors' knowledge, no such application of a hybrid model updating classical statistical forecasting with a deep learning neural network approach in the field of commercial real estate rent forecasting has been undertaken.

The authors propose novel tests for the detection of Markov switching deviations from forecast rationality. Existing forecast rationality tests either focus on constant deviations from forecast rationality over the full sample or are constructed to detect smooth deviations based on non-parametric techniques. In contrast, the proposed tests are parametric and have an advantage in detecting abrupt departures from unbiasedness and efficiency, which the authors demonstrate with Monte Carlo simulations. Using the proposed tests, the authors investigate whether Blue Chip Financial Forecasts (BCFF) for the Federal Funds Rate (FFR) are unbiased. The tests find evidence of a state-dependent bias: forecasters tend to systematically overpredict interest rates during periods of monetary easing, while the forecasts are unbiased otherwise. The authors show that a similar state-dependent bias is also present in market-based forecasts of interest rates, but not in the forecasts of real GDP growth and GDP deflator-based inflation. The results emphasize the special role played by monetary policy in shaping interest rate expectations above and beyond macroeconomic fundamentals.

The purpose of this paper is to examine the nature of Singapore's private housing market with respect to its price movement using time series models.

This paper analyses the price dynamics in the Singapore private housing market using the integrated autoregressive‐moving average modeling coupled with outlier detection and autoregressive conditional heteroskedasticity modeling techniques.

The paper finds that private house prices are better modeled as an ARIMA (1, 1, 0) model with corresponding dummy variables. This suggests that housing prices may be characterized as the combination of a stationary cyclical component and a non‐stationary stochastic growth component over the past almost three decades. This affirms that the Singapore's private housing market is characterised by the weak‐form inefficiency.

The results show that even though ARIMA with dummy variables performs better to ARIMA with ARCH in dynamic performance, there is only marginal improvement on the original model. This suggests that the method for selecting intervention variables in the ARIMA modeling is worth further research with the aim of improving its predictive ability.

This paper incorporates the detection of outliers and intervention procedure in the modeling in order to analyse the impacts of extraordinary events such the recent Asian financial crisis and excessive market speculation on property prices and take them into consideration in forecasting price changes.

An accurate long-term multi-step forecast provides crucial basic information for planning and reinforcing managerial decision-support. However, nonstationarity and nonlinearity, normally consisted of several types of managerial data can seriously ruin the forecasting computation. This paper aims to propose an effective long-term multi-step forecasting conjunction model, namely, wavelet–nonlinear autoregressive neural network (WNAR) conjunction model. The WNAR combines discrete wavelet transform (DWT) and nonlinear autoregressive neural network (NAR) to cope with such nonstationarity and nonlinearity within the managerial data; as a consequence, provides insight information that enhances accuracy and reliability of long-term multi-step perspective, leading to effective management decision-making.

Based on WNAR conjunction model, wavelet decomposition is executed for efficiently extracting hidden significant, temporal features contained in each of six benchmark nonstationary data sets from different managerial domains. Then, each extracted feature set at a particular resolution level is fed into NAR for the further forecast. Finally, NAR forecasting results are reconstructed. Forecasting performance measures throughout 1 to 30-time lags rely on mean absolute percentage error (MAPE), root mean square error (RMSE), Nash-Sutcliffe efficiency index or the coefficient of efficiency (E_f) and Diebold–Mariano (DM) test. An effect of data characteristic in terms of autocorrelation on forecasting performances of each data set are observed.

Long-term multi-step forecasting results show the best accuracy and high-reliability performance of the proposed WNAR conjunction model over some other efficient forecasting models including a single NAR model. This is confirmed by DM test, especially for the short-forecasting horizon. In addition, rather steady, effective long-term multi-step forecasting performances are yielded with slight effect from time lag changes especially for the data sets having particular high autocorrelation, relative against 95 per cent degree of confidence normal distribution bounds.

The WNAR, which combines DWT with NAR can be accounted as a bridge for the gap between machine learning, engineering signal processing and management decision-support systems. Thus, WNAR is referred to as a forecasting tool that provides insight long-term information for managerial practices. However, in practice, suitable exogenous input forecast factors are required on the managerial domain-by-domain basis to correctly foresee and effectively prepare necessary reasonable management activities.

Few works have been implemented to handle the nonstationarity, consisted of nonlinear managerial data to attain high-accurate long-term multi-step forecast. Combining DWT and NAR capabilities would comprehensively and specifically deal with the nonstationarity and nonlinearity difficulties at once. In addition, it is found that the proposed WNAR yields rather steady, effective long-term multi-step forecasting performance throughout specific long time lags regarding the data, having certainly high autocorrelation levels across such long time lags.

This chapter investigates the performance of different dimension reduction approaches for large vector autoregressions in multi-step ahead forecasts. The authors consider factor augmented VAR models using principal components and partial least squares, random subset regression, random projection, random compression, and estimation via LASSO and Bayesian VAR. The authors compare the accuracy of iterated and direct multi-step point and density forecasts. The comparison is based on macroeconomic and financial variables from the FRED-MD data base. Our findings suggest that random subspace methods and LASSO estimation deliver the most precise forecasts.

Structural models' inflation forecasts are often inferior to those of naïve devices. This chapter theoretically and empirically assesses this for UK annual and quarterly inflation, using the theoretical framework in Clements and Hendry (1998, 1999). Forecasts from equilibrium-correction mechanisms, built by automatic model selection, are compared to various robust devices. Forecast-error taxonomies for aggregated and time-disaggregated information reveal that the impacts of structural breaks are identical between these, helping to interpret the empirical findings. Forecast failures in structural models are driven by their deterministic terms, confirming location shifts as a pernicious cause thereof, and explaining the success of robust devices.

With the rise in wine consumption, accurate wine price forecasts have significantly impacted restaurant and hotel purchasing decisions and inventory management. This study aims to develop a precise and effective wine price point and interval forecasting model.

The proposed forecast model uses an improved hybrid kernel extreme learning machine with an attention mechanism and a multi-objective swarm intelligent optimization algorithm to produce more accurate price estimates. To the best of the authors’ knowledge, this is the first attempt at applying artificial intelligence techniques to improve wine price prediction. Additionally, an effective method for predicting price intervals was constructed by leveraging the characteristics of the error distribution. This approach facilitates quantifying the uncertainty of wine price fluctuations, thus rendering decision-making by relevant practitioners more reliable and controllable.

The empirical findings indicated that the proposed forecast model provides accurate wine price predictions and reliable uncertainty analysis results. Compared with the benchmark models, the proposed model exhibited superiority in both one-step- and multi-step-ahead forecasts. Meanwhile, the model provides new evidence from artificial intelligence to explain wine prices and understand their driving factors.

This study is a pioneering attempt to evaluate the applicability and effectiveness of advanced artificial intelligence techniques in wine price forecasts. The proposed forecast model not only provides useful options for wine price forecasting but also introduces an innovative addition to existing forecasting research methods and literature.