Search results

The purpose of this paper is to evaluate the forecasting performance of grey prediction models on educational attainment vis-à-vis that of exponential smoothing combined with multiple linear regression employed by the National Center for Education Statistics (NCES).

An out-of-sample forecasting experiment was carried out to compare the forecasting performances on educational attainments among GM(1,1), GM(1,1) rolling, FGM(1,1) derived from the grey system theory and exponential smoothing prediction combined with multivariate regression. The predictive power of each model was measured based on MAD, MAPE, RMSE and simple F-test of equal variance.

The forecasting efficiency evaluated by MAD, MAPE, RMSE and simple F-test of equal variance revealed that the GM(1,1) rolling model displays promise for use in forecasting educational attainment.

Since the possible inadequacy of MAD, MAPE, RMSE and F-type test of equal variance was documented in the literature, further large-scale forecasting comparison studies may be done to test the prediction powers of grey prediction and its competing out-of-sample forecasts by other alternative measures of accuracy.

The findings of this study would be useful for NCES and professional forecasters who are expected to provide government authorities and education policy makers with accurate information for planning future policy directions and optimizing decision-making.

As a continuing effort to evaluate the forecasting efficiency of grey prediction models, the present study provided accumulated evidence for the predictive power of grey prediction on short-term forecasts of educational statistics.

The purpose of this paper is to examine the applicability and capability of models based on a genetic algorithm and support vector machine (GA-SVM) and a genetic algorithm and relevance vector machine (GA-RVM) for the prediction of phytoplankton abundances associated with algal blooms in a Macau freshwater reservoir, and compare their performances with an artificial neural network (ANN) model.

The hybrid models GA-SVM and GA-RVM were developed for the optimal control of parameters for predicting (based on the current month’s variables) and forecasting (based on the previous three months’ variables) phytoplankton dynamics in a Macau freshwater reservoir, MSR, which has experienced cyanobacterial blooms in recent years. There were 15 environmental parameters, including pH, SiO₂, alkalinity, bicarbonate (HCO₃−), dissolved oxygen (DO), total nitrogen (TN), UV254, turbidity, conductivity, nitrate (NO₃−), orthophosphate (PO₄³⁻), total phosphorus (TP), suspended solids (SS) and total organic carbon (TOC) selected from the correlation analysis, with eight years (2001-2008) of data for training, and the most recent three years (2009-2011) for testing.

For both accuracy performance and generalized performance, the ANN, GA-SVM and GA-RVM had similar predictive powers of R² of 0.73-0.75. However, whereas ANN and GA-RVM models showed very similar forecast performances, GA-SVM models had better forecast performances of R² (0.862), RMSE (0.266) and MAE (0.0710) with the respective parameters of 0.987, 0.161 and 0.032 optimized using GA.

This is the first application of GA-SVM and GA-RVM models for predicting and forecasting algal bloom in freshwater reservoirs. GA-SVM was shown to be an effective new way for monitoring algal bloom problem in water resources.

Modelling, predicting and forecasting commercial rents are now seen as necessary and explicit processes in real estate investment. Decisions on the prospects for specific investments, the real estate portfolio and multi‐asset portfolio are made as a result of these processes and thus it is the accuracy of these models, predictions and forecasts in capturing future movements in rents that are implicitly tested in the marketplace. Despite the amount of theoretical and empirical research that has been conducted into modelling and predicting rents, it is unusual to find research which explicitly considers the predictive accuracy of models on an ex ante basis. This paper seeks to demonstrate the importance and possible value of such a procedure by examining the predictability of commercial rents in the office, industrial and retail markets of Great Britain over a real estate “cycle”. The paper concludes that theory appears to be a better indicator of the “correct” model structure than maximising historic fit. Often naïve competitors are better predictors than the model selection strategy employed.

This paper aims to propose a hybrid-forecasting model for long-term tourism demand forecasting. As such, it attempts to model the tourism demand in the Philippines, which is a relatively underrepresented area in the literature, despite its tourism sector’s growing economic progress.

A hybrid support vector regression (SVR) – seasonal autoregressive integrated moving averages (SARIMA) model is proposed to model the seasonal, linear and nonlinear components of the tourism demand in a destination country. The paper further proposes the use of multiple criteria decision-making (MCDM) approaches in selecting the best forecasting model among a set of considered models. As such, a preference ranking organization method for enrichment of evaluations (PROMETHEE) II is used to rank the considered forecasting models.

The proposed hybrid SVR-SARIMA model is the best performing model among a set of considered models in this paper using performance criteria that evaluate the errors of magnitude, directionality and trend change, of a forecasting model. Moreover, the use of the MCDM approach is found to be a relevant and prospective approach in selecting the best forecasting model among a set of models.

The novelty of this paper lies in several aspects. First, this paper pioneers the demonstration of the SVR-SARIMA model’s capability in forecasting long-term tourism demand. Second, this paper is the first to have proposed and demonstrated the use of an MCDM approach for performing model selection in forecasting. Finally, this paper is one of the very few papers to provide lenses on the current status of Philippine tourism demand.

The purpose of this paper is to give a comprehensive review and synthesis of automated textual analysis of corporate disclosure to show how the accuracy of disclosure tone has been incremented with the evolution of developed automated methods that have been used to calculate tone in prior studies.

This study have conducted the survey on “automated textual analysis of corporate disclosure and its impact” by searching at Google Scholar and Scopus research database after the year 2000 to prepare the list of papers. After classifying the prior literature into a dictionary-based and machine learning-based approach, this study have again sub-classified those papers according to two other dimensions, namely, information sources of disclosure and the impact of tone on the market.

This study found literature on how value relevance of tone is varied with the use of different automated methods and using different information sources. This study also found literature on the impact of such tone on market. These are contributing to help investor’s decision-making and earnings and returns prediction by researchers. The literature survey shows that the research gap lies in the development of methodologies toward the calculation of tone more accurately. This study also mention how different information sources and methodologies can influence the change in disclosure tone for the same firm, which, in turn, may change market performance. The research gap also lies in finding the determinants of disclosure tone with large scale data.

After reviewing some papers based on automated textual analysis of corporate disclosure, this study shows how the accuracy of the result is incrementing according to the evolution of automated methodology. Apart from the methodological research gaps, this study also identify some other research gaps related to determinants (corporate governance, firm-level, macroeconomic factors, etc.) and transparency or credibility of disclosure which could stimulate new research agendas in the areas of automated textual analysis of corporate disclosure.

Multi-let industrial (MLI) estates are an emerging £15 billion UK real estate asset class that can offer attractive returns, a diversified income base, constrained supply and extensive management opportunities to add value within an operational platform. This investment appeal is supported by the evolving MLI occupier market with the growth of small to medium enterprises (SME) requiring modern urban business space driven in part by technology advances offering new streams of supply chain connectivity between businesses and potential clients at a local level.

To understand more about MLI properties, this study utilises a hedonic pricing model to quantify property values as a function of defined variables. The dataset used for this research is a sample portfolio of 26 multi-let industrial properties. The dataset was analysed alongside eleven physical, financial and locational factors. Interestingly, the hedonic pricing model results showed that only four characteristics are value-affecting across the selected properties: namely (1) Granularity of the property income, (2) Distance from the nearest motorway, (3) Distance to the nearest town centre and (4) Gross internal floor area. A chi–test confirmed that there was no significant difference between the modelled values and the supplied property valuations.

This preliminary study offers valuable insight into MLI property market drivers and could easily form a simple decision-making tool to examine potential MLI opportunities in this developing real estate asset class.

In detailing these key MLI property features, current research is limited and focused primarily on market commentary. New knowledge on the MLI property market can provide a platform creating interesting opportunities for fund managers with an intensive management engagement strategy.

This study aims to explore the structure and dynamics of Qatar’s crowdfunding ecosystem to support economic diversification and enhance entrepreneurial activities. This research focuses on analyzing the development of the industry, its regulatory environment and the collaborative dynamics among stakeholders.

This study used network analysis and Monte Carlo simulations to examine the interplay between various stakeholders, including entrepreneurs, to understand their roles and interconnections. This study also simulated different economic scenarios to evaluate the potential impact of crowdfunding under various market conditions and regulatory frameworks.

The analysis reveals a moderate level of crowdfunding activity characterized by conservative fundraising outcomes. The key factors identified include the pivotal role of a supportive regulatory framework and the necessity of robust stakeholder collaboration and infrastructure to ensure the industry’s resilience and growth.

The findings are constrained by the simulated scenarios and the current state of the crowdfunding market in Qatar, suggesting that further research could explore emerging trends as the market evolves.

This study provides actionable recommendations for policymakers and regulatory authorities to boost a conducive environment for crowdfunding platforms. This includes enhancing connectivity among stakeholders and building robust infrastructure to support industry growth.

This study underlines the significant social benefits of crowdfunding, including promoting innovation, supporting economic growth and facilitating entrepreneurship. These elements are vital to Qatar’s broader economic diversification strategy.

This study provides original insights into the crowdfunding landscape in Qatar, particularly in terms of strategic planning and risk management, using advanced simulation techniques to predict the outcomes of different regulatory and economic scenarios.

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.