Search results

The purpose of the study is to examine the efficiency of linear, nonlinear and artificial neural networks (ANNs), in predicting property prices.

The present study uses a dataset of 1,468 real estate transactions from 2020 to 2022, obtained from the Department of Property Taxes of Republic of Kosovo. Beginning with a fundamental linear regression model, the study tackles the question of overlooked nonlinearity, employing a similar strategy like Peterson and Flanagan (2009) and McCluskey et al. (2012), whereby ANN's predictions are incorporated as an additional regressor within the ordinary least squares (OLS) model.

The research findings underscore the superior fit of semi-log and double-log models over the OLS model, while the ANN model shows moderate performance, contrary to the conventional conviction of ANN's superior predictive power. This is notably divergent from the prevailing belief about ANN's superior predictive power, shedding light on the potential overestimation of ANN's efficacy.

The study accentuates the importance of embracing diverse models in property price prediction, debunking the notion of the ubiquitous applicability of ANN models. The research outcomes carry substantial ramifications for both scholars and professionals engaged in property valuation.

Distinctively, this research pioneers the comparative analysis of diverse models, including ANN, in the setting of a developing country's capital, hence providing a fresh perspective to their effectiveness in property price prediction.

This study aims to predict China's carbon emission intensity and put forward a set of policy recommendations for further development of a low-carbon economy in China.

In this paper, the Interaction Effect Grey Power Model of N Variables (IEGPM(1,N)) is developed, and the Dragonfly algorithm (DA) is used to select the best power index for the model. Specific model construction methods and rigorous mathematical proofs are given. In order to verify the applicability and validity, this paper compares the model with the traditional grey model and simulates the carbon emission intensity of China from 2014 to 2021. In addition, the new model is used to predict the carbon emission intensity of China from 2022 to 2025, which can provide a reference for the 14th Five-Year Plan to develop a scientific emission reduction path.

The results show that if the Chinese government does not take effective policy measures in the future, carbon emission intensity will not achieve the set goals. The IEGPM(1,N) model also provides reliable results and works well in simulation and prediction.

The paper considers the nonlinear and interactive effect of input variables in the system's behavior and proposes an improved grey multivariable model, which fills the gap in previous studies.

Due to the miniaturization of electronic devices, the increased current density through solder joints leads to the occurrence of electromigration failure, thereby reducing the reliability of electronic devices. The purpose of this study is to propose a finite element-artificial neural network method for the prediction of temperature and current density of solder joints, and thus provide reference information for the reliability evaluation of solder joints.

The temperature distribution and current density distribution of the interconnect structure of electronic devices were investigated through finite element simulations. During the experimental process, the actual temperature of the solder joints was measured and was used to optimize the finite element model. A large amount of simulation data was obtained to analyze the neural network by varying the height of solder joints, the diameter of solder pads and the magnitude of current loads. The constructed neural network was trained, tested and optimized using this data.

Based on the finite element simulation results, the current is more concentrated in the corners of the solder joints, generating a significant amount of Joule heating, which leads to localized temperature rise. The constructed neural network is trained, tested and optimized using the simulation results. The ANN 1, used for predicting solder joint temperature, achieves a prediction accuracy of 96.9%, while the ANN 2, used for predicting solder joint current density, achieves a prediction accuracy of 93.4%.

The proposed method can effectively improve the estimation efficiency of temperature and current density in the packaging structure. This method prevails in the field of packaging, and other factors that affect the thermal, mechanical and electrical properties of the packaging structure can be introduced into the model.

The variance between the winning bid and the owner's estimated cost (OEC) is one of the construction management risks in the pre-tendering phase. The study aims to enhance the quality of the owner's estimation for predicting precisely the contract cost at the pre-tendering phase and avoiding future issues that arise through the construction phase.

This paper integrated artificial neural networks (ANN), deep neural networks (DNN) and time series (TS) techniques to estimate the ratio of a low bid to the OEC (R) for different size contracts and three types of contracts (building, electric and mechanic) accurately based on 94 contracts from King Saud University. The ANN and DNN models were evaluated using mean absolute percentage error (MAPE), mean sum square error (MSSE) and root mean sums square error (RMSSE).

The main finding is that the ANN provides high accuracy with MAPE, MSSE and RMSSE a 2.94%, 0.0015 and 0.039, respectively. The DNN's precision was high, with an RMSSE of 0.15 on average.

The owner and consultant are expected to use the study's findings to create more accuracy of the owner's estimate and decrease the difference between the owner's estimate and the lowest submitted offer for better decision-making.

This study fills the knowledge gap by developing an ANN model to handle missing TS data and forecasting the difference between a low bid and an OEC at the pre-tendering phase.

Bitcoin (BTC) is significantly correlated with global financial assets such as crude oil, gold and the US dollar. BTC and global financial assets have become more closely related, particularly since the outbreak of the COVID-19 pandemic. The purpose of this paper is to formulate BTC investment decisions with the aid of global financial assets.

This study suggests a more accurate prediction model for BTC trading by combining the dynamic conditional correlation generalized autoregressive conditional heteroscedasticity (DCC-GARCH) model with the artificial neural network (ANN). The DCC-GARCH model offers significant input information, including dynamic correlation and volatility, to the ANN. To analyze the data effectively, the study divides it into two periods: before and during the COVID-19 outbreak. Each period is then further divided into a training set and a prediction set.

The empirical results show that BTC and gold have the highest positive correlation compared with crude oil and the USD, while BTC and the USD have a dynamic and negative correlation. More importantly, the ANN-DCC-GARCH model had a cumulative return of 318% before the outbreak of the COVID-19 pandemic and can decrease loss by 50% during the COVID-19 pandemic. Moreover, the risk-averse can turn a loss into a profit of about 20% in 2022.

The empirical analysis provides technical support and decision-making reference for investors and financial institutions to make investment decisions on BTC.

By examining the impact of product innovation on abnormal financial returns following the launch of new products, this study aims to test the explanatory power of a new compound measure of product innovativeness (Ganbaatar and Douglas, 2019).

It is a longitudinal study in which the authors used the compound product innovativeness score (CPIS) for the first time to measure product innovativeness. The abnormal financial returns are estimated through the event study design, where four different models are used. Artificial neural network analysis is done to determine the impact of the CPIS on abnormal returns by utilising a hexic polynomial regression model.

The authors find effect sizes that substantially exceed practically significant levels and that the CPIS explain 65% of the variance in the firm’s abnormal returns in market valuation. Moreover, new-to-the-market novelty predicts 83% of the variation, while new-to-the-firm (catch-up) innovation insignificantly impacts firm value.

This paper demonstrates how the CPIS, an objective and direct measure of product innovativeness, can be used to gain more insight into the innovation effect.

Implications for the business practice of this study include the necessity of relentless innovation by firms in contested differentiated markets, particularly where technological advance is ongoing. Larger and mature firms must practice corporate entrepreneurship to renew their products on a continuous basis to avoid slipping backwards in their markets. Innovation leadership, rather than following the leader, is also important to increase competitive advantage, given the result that innovation followship does not produce abnormal financial returns.

In this study, the authors focused on the effect of product innovativeness on firm performance. While the literature affirms a positive relationship between innovation and firm performance, the effect size of this relationship varies, due largely to the authors contend to simplistic measures of innovativeness. In this study, the authors adopt the relatively novel “compound” measure of product innovativeness (Ganbaatar and Douglas, 2019) to better encapsulate the nuances of both technical novelty and market novelty. This measure of product innovativeness is applicable to firms of all sizes but is more easily applied to entrepreneurial new ventures and SMEs, and it avoids the shortcomings of prior firm-level and subjective measures of innovativeness for both smaller and larger firms. Using a more effective analytical method (Artificial Neural Network), the authors investigated whether there is a “practically” significant effect size due to product innovation, which could be valuable for entrepreneurs in practice. The authors show that the CPIS measure can very effectively explain abnormalities in the stock market, exhibiting a moderate effect size and explaining 65% of the variation in abnormal returns.

This paper aims to develop a novel grey Bernoulli model with memory characteristics, which is designed to dynamically choose the optimal memory kernel function and the length of memory dependence period, ultimately enhancing the model's predictive accuracy.

This paper enhances the traditional grey Bernoulli model by introducing memory-dependent derivatives, resulting in a novel memory-dependent derivative grey model. Additionally, fractional-order accumulation is employed for preprocessing the original data. The length of the memory dependence period for memory-dependent derivatives is determined through grey correlation analysis. Furthermore, the whale optimization algorithm is utilized to optimize the cumulative order, power index and memory kernel function index of the model, enabling adaptability to diverse scenarios.

The selection of appropriate memory kernel functions and memory dependency lengths will improve model prediction performance. The model can adaptively select the memory kernel function and memory dependence length, and the performance of the model is better than other comparison models.

The model presented in this article has some limitations. The grey model is itself suitable for small sample data, and memory-dependent derivatives mainly consider the memory effect on a fixed length. Therefore, this model is mainly applicable to data prediction with short-term memory effect and has certain limitations on time series of long-term memory.

In practical systems, memory effects typically exhibit a decaying pattern, which is effectively characterized by the memory kernel function. The model in this study skillfully determines the appropriate kernel functions and memory dependency lengths to capture these memory effects, enhancing its alignment with real-world scenarios.

Based on the memory-dependent derivative method, a memory-dependent derivative grey Bernoulli model that more accurately reflects the actual memory effect is constructed and applied to power generation forecasting in China, South Korea and India.

This paper presents the findings from the assessment of the determinants of cloud computing (CC) deployment by construction organisations. Using the technology-organisation-environment (TOE) framework, the study strives to improve construction organisations' project delivery and digital transformation by adopting beneficial technologies like CC.

This study adopted a post-positivism philosophical stance using a deductive approach with a questionnaire administered to construction organisations in South Africa. The data gathered were analysed using descriptive and inferential statistics. Also, the fusion of structural equation modelling (SEM) and machine learning (ML) regression models helped to gain a robust understanding of the key determinants of using CC.

The study found that the use of CC by construction organisations in South Africa is still slow. SEM indicated that this slow usage is influenced by six technology and environmental factors, namely (1) cost-effectiveness, (2) availability, (3) compatibility, (4) client demand, (5) competitors' pressure and (6) trust in cloud service providers. ML models developed affirmed that these variables have high predictive power. However, sensitivity analysis revealed that the availability of CC and CC's ancillary technologies and the pressure from competitors are the most important predictors of CC usage in construction organisations.

The paper offers a theoretical backdrop for future works on CC in construction, particularly in developing countries where such a study has not been explored.

In the context of a developing country, Indian buildings need further research to channelize energy needs optimally to reduce energy wastage, thereby reducing carbon emissions. Also, reduction in smart devices’ costs with sequential advancements in Information and Communication Technology have resulted in an environment where model predictive control (MPC) strategies can be easily implemented. This study aims to propose certain preemptive measures to minimize the energy costs, while ensuring the thermal comfort for occupants, resulting in better greener solutions for building structures.

A simulation-based multi-input multi-output MPC strategy has been proposed. A dual objective function involving optimized energy consumption with acceptable thermal comfort has been achieved through simultaneous control of indoor temperature, humidity and illumination using various control variables. A regression-based lighting model and seasonal auto-regressive moving average with exogenous inputs (SARMAX) based temperature and humidity models have been chosen as predictor models along with four different control levels incorporated.

The mathematical approach in this study maintains an optimum tradeoff between energy cost savings and satisfactory occupants’ comfort levels. The proposed control mechanism establishes the relationships of output variables with respect to control and disturbance variables. The SARMAX and regression-based predictor models are found to be the best fit models in terms of accuracy, stability and superior performance. By adopting the proposed methodology, significant energy savings can be accomplished during certain hours of the day.

This study has been done on a specific corporate entity and future analysis can be done on other corporate or residential buildings and in other geographical settings within India. Inclusion of sensitivity analysis and non-linear predictor models is another area of future scope.

This study presents a dynamic MPC strategy, using five disturbance variables which further improves the overall performance and accuracy. In contrast to previous studies on MPC, SARMAX model has been used in this study, which is a novel contribution to the theoretical literature. Four levels of control zones: pre-cooling, strict, mild and loose zones have been used in the calculations to keep the Predictive Mean Vote index within acceptable threshold limits.

Recent studies have observed rise in consumer’s ethical concerns about the online retailers while making a purchase decision. The impetus for businesses to use corporate social responsibility (CSR) is evident, but the effects of CSR motives on corresponding processes underlying cause-related marketing (CRM) patronage intention have not been thoroughly examined. This study, anchored on attribution theory, established a research model that better explains the influence of CSR motives on patronage intentions toward CRM-oriented online retailers. Additionally, this study aims to examine the moderating role of spirituality (SPT) on CSR motives and CRM patronage intention (CPI).

Primary data has been collected from 722 respondents and analyzed by using deep neural-network architecture by using the innovative PLS-SEM-ANN method to predict/rank the factors impacting CPI.

The results revealed the normalized importance of the predictors of CPI and found that value-driven motive was the strongest predictor, followed by strategic motive, SPT, age and stakeholder-driven motive. In contrast, egoistic motive, education and income were found insignificant.

The pandemic has transformed the way consumers shop and fortified the online economy, thereby resulting in a paradigm shift toward usage of e-commerce platforms. The results offer valuable insights to online retailers and practitioners for predicting patronage intentions by CSR motives and, thus, effectively engage CRM consumers by designing promotions in a way that would deeply resonate with them. This study assessed and predicted the factors influencing the CPI s, thereby guiding the online retailers to design CSR strategies and manage crucial CRM decisions.