Search results

Stock prices are subject to the influence of news and social media, and a discernible co-movement pattern exists among multiple stocks. Using a knowledge graph to represent news semantics and establish connections between stocks is deemed essential and viable.

This study presents a knowledge-driven framework for predicting stock prices. The framework integrates relevant stocks with the semantic and emotional characteristics of textual data. The authors construct a stock knowledge graph (SKG) to extract pertinent stock information and use a knowledge graph representation model to capture both the relevant stock features and the semantic features of news articles. Additionally, the authors consider the emotional characteristics of news and investor comments, drawing insights from behavioral finance theory. The authors examined the effectiveness of these features using the combined deep learning model CNN+LSTM+Attention.

Experimental results demonstrate that the knowledge-driven combined feature model exhibits significantly improved predictive accuracy compared to single-feature models.

The study highlights the value of the SKG in uncovering potential correlations among stocks. Moreover, the knowledge-driven multi-feature fusion stock forecasting model enhances the prediction of stock trends for well-known enterprises, providing valuable guidance for investor decision-making.

This study aims to examine whether Chinese firms increase their concerns about analysts’ earnings forecasts following the split-share structure reform (SSR) in 2005, which removed trading restrictions on approximately 70% of the shares of listed firms.

Using data from 2002 to 2019, the authors empirically test the association between meeting or beating analysts’ earnings expectations and the implementation of SSR.

The authors find that firms are more inclined to meet analysts’ earnings expectations after the introduction of SSR. Further analysis shows that firms guide analysts to walk their forecasts down by manipulating third-quarter earnings, suggesting enhanced value relevance between analysts’ forecasts and third-quarter earnings management in the postreform period.

The findings reveal an undesirable side effect of SSR and suggest that policymakers and regulators should consider and carefully manage the complex relationships between firms and analysts.

In contrast to prior studies that predominantly focus on the positive effects of the reform, this study reveals the side effects of SSR and provides new evidence on the mechanisms of meeting or beating analysts’ earnings expectations.

Although improving customer experience (CX) has always been one of the top priorities of business process management (BPM), the evidence on the actual contribution made by traditional BPM to improving CX and customer experience management (CXM) is mixed. Recently, new and enhanced capability areas have been added to the traditional BPM frameworks, yet it is unclear which of them contribute to CXM. Moreover, it is not known which of them are necessary and which are sufficient conditions. The aim of this research is to shed light on the research gap concerning which BPM capabilities, especially new and enhanced ones, are relevant to CXM.

Quantitative data from 268 medium and large companies in 3 EU countries were analysed using hierarchical linear regression analysis and necessary condition analysis.

The results show that traditional BPM capabilities are a necessary condition for CXM, but with minor significance. Most highly significant necessary conditions and also most highly or medium significant sufficient conditions belong to the People or Culture area. Agile Process Improvement is the only new or enhanced BPM capability area in the Methods/IT area that is a necessary and also a sufficient condition for CXM maturity. Advanced Process Digitalisation was identified as neither a significant necessary nor a sufficient condition for CXM.

This research contributes to better understanding of the role played by BPM for CXM, where previous research provides mixed results.

With increased focus on data literacy and data science education in K-12, little is known about what makes a data set preferable for use by classroom teachers. Given that educational designers often privilege authenticity, the purpose of this study is to examine how teachers use features of data sets to determine their suitability for authentic data science learning experiences with their students.

Interviews with 12 practicing high school mathematics and statistics teachers were conducted and video-recorded. Teachers were given two different data sets about the same context and asked to explain which one would be better suited for an authentic data science experience. Following knowledge analysis methods, the teachers’ responses were coded and iteratively reviewed to find themes that appeared across multiple teachers related to their aesthetic judgments.

Three aspects of authenticity for data sets for this task were identified. These include thinking of authentic data sets as being “messy,” as requiring more work for the student or analyst to pore through than other data sets and as involving computation.

Analysis of teachers’ aesthetics of data sets is a new direction for work on data literacy and data science education. The findings invite the field to think critically about how to help teachers develop new aesthetics and to provide data sets in curriculum materials that are suited for classroom use.

Much research has explored high levels of son preference in India, finding that parents often report a desire for more sons than daughters. While scholars have noted that a nontrivial portion of respondents claim to have no sex preference, little is known about (1) the characteristics of this group and (2) how such parental preferences relate to child outcomes. We use data from a representative study of rural South Indian households (n = 7,891 adults) to address these gaps. Descriptive results show that a sizable portion of respondents – one in four – indicated that, at the start of their marriage, they had no preference for the number of daughters or sons they wanted. Further, multinomial regression results show that those who reported no sex preference at the time of marriage were more likely to be female, older, and less likely to be sterilized than those who reported equal or son preference, with additional distinctions across educational attainment and religion. Turning to child-level outcomes, we examined whether parents’ sex preferences related to adolescent mental health through ordinary least squares (OLS) regression models (n = 1,245 adolescents). Adolescents whose mothers stated no sex preference reported significantly fewer anxiety and depressive symptoms than their peers. Fathers’ sex preferences were not significantly related to adolescent mental health. These findings suggest that a lack of sex preference may hold meaningful and positive implications for adolescent mental health. Further, although son preference is a widespread phenomenon, singular attention on those with son preference may mask important nuances among Indian families.

The objective of the study is to explore the mediatory role of the environmental performance of organisations on their economic and social performances. It demonstrates that implementing environmental management techniques should not only be done to comply with environmental regulations, but also as a means of improving social and economic performance.

The data were gathered from the manufacturing industry of Zimbabwe, and 302 useable responses were received. Data analysis was performed through structural equation modelling (SEM) using SMART PLS 3.

Improvement in environmental performance led to improvements in both social and economic performances. Also, environmental performance contributes the greatest total effect; hence, it deserves attention, not only for compliance but also for economic reasons.

Our goal is to quantify the extent to which environmental performance might improve the social and, more importantly, the economic performance of organisations. The study also explores the relative importance and performance of lean manufacturing (LM), green manufacturing (GM), social performance and environmental performance for purposes of prioritisation of organisational improvement initiatives.

Outside of teaching, little knowledge exists about the emotion work of pedagogical professionals, i.e., the emotion work that is performed in kindergartens, residential homes or school counseling. This study addresses this shortcoming by answering the questions (1) how is emotion work experienced and coped with in pedagogical professions? and (2) how does pedagogical professionals’ emotion work relate to burnout?

An exploratory sequential mixed methods approach consisting of an interview and a questionnaire was applied. First, n = 10 interviews were conducted to investigate how emotion work is experienced and managed by pedagogical professionals. Second, hypotheses regarding the relationship between identified resources and burnout were derived and empirically tested in a questionnaire survey with n = 97 participants.

The interviews provided insight into various emotional job demands and resources. Emotion work has been shown to be a key aspect of pedagogical work. Detached concern was identified as an emotion-regulating resource in coping with the resulting emotional job demands. The results of the quantitative phase revealed that pedagogical professionals’ detached concern plays a vital role in preventing burnout.

This study adds new insights to the understanding of emotion work performed in care work professions outside of teaching. The acknowledgement of pedagogical work, as skilled (emotion) work, and the investigation of resources is an important step in improving the working conditions of pedagogical professionals and thus protecting their health and well-being.

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.

This study aims to examine the influence of organizational flexibility (OF) and shared vision (SV) on sustainable competitive advantage (SCA) with the mediation role of responsible innovation (RI) in the manufacturing industry of a developing country. Furthermore, big data analytics capability (BDAC) serves as a moderator between RI and SCA.

The study's hypotheses are investigated using the structural equation modeling (SEM) method. Through simple random sampling, information was gathered from 247 owners/managers of manufacturing SMEs.

The results elucidate that OF and SV significantly determine RI and SCA. Moreover, RI significantly mediates between SV, OF and SCA. Besides, RI significantly determines SCA. BDAC significantly leads to SCA. Finally, BDAC significantly moderates between RI and SCA.

RI is crucial for manufacturing small and medium-sized enterprises (SMEs) to gain SCA and BDAC is important to address the changing demands of consumers for environment-friendly products. This study gives the public an overview of the different degrees to which SMEs are embracing RI and BDAC; with more environment-friendly initiatives, the natural environment will become more sustainable. Environmental sustainability will benefit each individual living in society.

This study adds value to the existing literature by focusing on predictors that affect SCA. Using dynamic capability theory, this initial study examines the influence of SV and OF on SCA and RI as mediators. Furthermore, BDAC is used as a moderating variable between RI and SCA. Managers, students and researchers can benefit from this study.

With the growth of organizations and businesses, customer acquisition and retention processes have become more complex in the long run. That is why customer lifetime value (CLV) has become crucial to sales managers. Predicting the CLV is a strategic weapon and competitive advantage in increasing profitability and identifying customers with more splendid profitability and is one of the essential key performance indicators (KPI) used in customer segmentation. Thus, this paper proposes a stacked ensemble learning method, a combination of multiple machine learning methods, for CLV prediction.

In order to utilize customers’ behavioral features for predicting the value of each customer’s CLV, the data of a textile sales company was used as a case study. The proposed stacked ensemble learning method is compared with several popular predictive methods named deep neural networks, bagging support vector regression, light gradient boosting machine, random forest and extreme gradient boosting.

Empirical results indicate that the regression performance of the stacked ensemble learning method outperformed other methods in terms of normalized rooted mean squared error, normalized mean absolute error and coefficient of determination, at 0.248, 0.364 and 0.848, respectively. In addition, the prediction capability of the proposed method improved significantly after optimizing its hyperparameters.

This paper proposes a stacked ensemble learning method as a new method for accurate CLV prediction. The results and comparisons support the robustness and efficiency of the proposed method for CLV prediction.