Aiming at the problems existing in the optimal allocation of financial resources, this paper establishes an optimization model and calculates the optimal allocation coefficient. With the help of Markowitz's investment theory, two indicators, which are investment risk and return rate, are analyzed quantitatively. First, by analyzing the allocation efficiency and risk of financial resources, the allocation efficiency model is established, and the problem is decomposed into a finite 0-1 programming problem, which is solved by Hungarian Method. Secondly, considering the minimum allocation risk and the expected maximum return, the multi-objective model is solved by progressive optimal algorithm. The model reflects both unsatisfaction and risk avoidance which are the two characteristics of rational investment behavior. The analysis shows that the model has strong applicability and can be expected to improve the allocation efficiency of financial resources and reduce the allocation risk.

Credit scoring, aiming to distinguish potential loan defaulter, has played an important role in the financial industry. To further improve the accuracy and efficiency of classification, this paper develops an ensemble model combined extreme gradient boosting (XGBoost) and deep neural network (DNN). In the method, training set is divided into different subsets by bagging sampling at first. Then, each subset is trained as a feature extractor by DNN and the extracted features is taken as the input of XGBoost to construct the base classifier. At last, the prediction result is the average of outputs of different base classifiers. In the training verification process, three credit datasets from the UCI machine learning repository are used to evaluate the proposed model. The outcome shows that this model is superior with a significant improvement.

Based on iceberg theory and the questionnaire of competency's elements, hierarchical index system of evaluation of teachers' innovation and entrepreneurship competency in universities is established. Through researches, the authors think that analytic hierarchy process (AHP) is a more scientific and reasonable evaluation method whose rationality is checked by satisfactory consistency while the evaluation model of artificial neutral network doesn't consider weighting. If the samples are more than 30, the evaluation of neural network model of teachers' innovation and entrepreneurship competency can achieve the accurate results and satisfactory requirements. Since the method of artificial neutral network has advantages of strong operability, simple rules, and minor errors, it can greatly reduce the workload because it not only eliminates human subjectivity of evaluation and greatly simplifies the process of evaluation, but also improves working efficiency and provides a new way of thinking for evaluation of the teachers' innovation and entrepreneurship competency in universities.

This study utilized an extended model of the Unified Theory of Acceptance and Use of Technology (UTAUT2) to explore the factors influencing the future adoption of accounting information systems (AIS) by Qatari students. A research model was proposed to predict future adoption, partially moderated by voluntary status of using the system. A sample of 237 students was used to probe their perceptions regarding the use of such systems in their future careers. Students were enrolled in an accounting information systems course in Qatar University. Results indicated that perceived facilitating conditions, performance expectancy and enjoyment were significant predictors of AIS. The other factors failed to be significant predictors. The estimated R2 was 48.4%. The moderation effect of voluntariness was also significant in influencing the relationship between enjoyment and future adoption. The moderator yielded a negative beta, which means that it faded the relationship under consideration. Conclusions and future recommendations are reported at the end of the paper.

This study explores the factors contributing to online users' network centrality in a network on Twitter in the context of a social movement about the “clear the shelters” campaign across the United States. The authors performed a social network analysis on a network including 13,270 Twitter users and 24,354 relationships to reveal users' betweenness, closeness, eigenvector, in-degree, and out-degree centralities before hypothesis testing. They applied a path analysis including users' centrality measures and their user-related features. The path analysis discovered that the factors of the number of people a user follows, the number of followers a user has, and the number of years since a user had his account increased a user's in-degree connections in the network. Together with the user's out-degree connections along with in-degree links, they pushed a user to have a strategic place in the network. They also implemented a multi-group analysis to find whether the impact of these factors showed differences specifically in replies to, mentions, and retweets networks.

The emergence of the new economic model of Internet credit industry brings convenience to people's lives, and it also impacts the business model of traditional commercial banking to a great extent. How to better improve the operation mode, correctly assess and avoid the risks of Internet finance, and create a healthy, orderly, safe and sustainable development environment of Internet finance industry is an important research topic in this industry under the current situation. This paper studies the application of innovative risk early warning model based on big data technology in Internet credit financial risk assessment, aiming at maximizing the utilization efficiency of internal and external data, building a timely, accurate and effective early warning system with independent characteristics, and creating a sharp weapon for intelligent risk early warning. In order to promote the healthy and benign development of China's Internet finance industry.

Prior studies have found that mobile cloud computing could bring substantial cost savings to firms, ultimately resulting in reduced transaction cost to customers. Despite this, financial firms in Fiji are slow adopters of mobile cloud computing. The study identifies the challenges faced by financial firms in the adoption of mobile cloud computing to advance the literature on innovation adoption with evidence from a unique context – a Pacific island country. The context is important as the issues are likely to be similar in other developing and remote island countries but the extant research is largely confined to developed countries. Our findings suggest that the lack of mobile cloud computing policy, infrastructure constraints, and security constraints, among others are the main barriers to the adoption thereof. The study contributes by presenting a revised model based on factors that emerged from the study.

Abstract— Machine learning can be used to provide systems the ability to automatically learn and improve from experiences without being explicitly programmed. It is fundamentally a multidisciplinary field that draws on results from Artificial intelligence, probability and statistics, information theory and analysis, among other fields that impact the field of Machine Learning. Ensemble methods are techniques that can be used to improve the predictive ability of a Machine Learning model. An ensemble comprises of individually trained classifiers whose predictions are combined when classifying instances. Some of the currently popular ensemble methods include Boosting, Bagging and Stacking. In this paper, we review these methods and demonstrate why ensembles can often perform better than single models. Additionally, some new experiments are presented to demonstrate the computational ability of Stacking approach.

In today's world, around 230 million people used the Bengali or Bangla language to communicate. These individuals are progressively associated with online exercises on famous micro-blogging and long-range interpersonal communication locales, imparting insights what's more, musings, and also the vast majority of articles are in the Bengali language. Thus, Bengali people express their emotions using the Bangla language by reviewing, commenting, or recommendations. Sentiment analysis helps determine the people's emotions expressed on social media or several online platforms. Therefore, this study focused on extracting their emotion from a Bengali text by utilizing Word2vector, Skip-Gram, and Continuous Bag of Words (CBOW) with a new Word to Index model by focusing on three individual classes happy, angry, and excited. The authors achieved the highest accuracy of 75% by utilizing the skip-gram model to classify those three types of emotions. This study also outperformed other existing works with LSTM, CNN model with existing datasets.

This study investigated the utility of the Internet of Things in the public sector and the factors influencing the satisfaction of its users. The study followed two directions, the first investigated managers’ perceptions and their satisfaction with using sensors for tracking vehicles. The second direction investigated drivers’ satisfaction with the system used. Results collected from 20 interviews conducted with managers revealed that cost reduction and more control over drivers’ behaviors are the contributions expected from the system. They reported the dissatisfaction of drivers based on violation of their privacy, inequity of implementation, and the low awareness of its utility. Surveys collected from drivers supported the role of trust and privacy, but failed to support the role of usefulness. The qualitative and quantitative nature of this research revealed valuable insights and concluded to important recommendations and future work.