Search

We adopt the classical Fama and French (1992) [E.F. Fama, K.R. French, The Cross-Section of Expected Stock Returns, The Journal of Finance, 47 (1992) 427 -- 465.] approach to investigate the effect of Beta, size, leverage, book value to market value (B/P), and earnings to price (E/P) ratio on the average monthly returns in the China Stock Market (CSM) from July 1998 to June 2011. The phenomenon of concept drift was found in this research. Our results indicate that the B/P has a significant negative correlation with the monthly average returns during this period, in contrast to the positive correlation found by a previous study by Wang and Di Iorio (2007) [Y. Wang, A. Di Iorio, The cross section of expected stock returns in the Chinese A-share market, Global Finance Journal, 17 (2007) 335 -- 349.] that covered from July 1996 to June 2002. Meanwhile the small-firm effect remains significant. Thus, while the behavioral or institutional factors may account for the counter-intuitive finding of the effect of value in the transitional economy, the relationship between fundamental characteristics and stock returns is more complex in China and warrants more rigorous investigation. Further, we suggest that autonomic and cloud computing system has a number of potential applications in stock market concept drift mining.

Many risk factors affect software development and risk management has become one of the major activities in software development. Discovering causal directions among risk factors and project performance are important support for risk management. The Additive Noise Model (ANM) is an effective algorithm for discovering the direction on one-to-one causalities, but ineffective on many-to-one causalities which are frequent in software project risk analysis (SPRA) process. Thus we proposed a modified ANM with Conditional Probability Table (ANMCPT) to discover the causal direction among risk factors and project performance. The experimental results show our proposed algorithm is effective to discover the many-to-one causalities in SPRM on 498 collected software project data, and it performs better than other algorithms in the prediction with discovered causes of project performance, such as logistic regression, C4.5, Naive Bayes, and general BNs. This study firstly presents an approach using ANM for many-to-one causality discovery in SPRA and then proves that it is an effective algorithm for analyzing the risk in software project.

In China stock market, more than 95% are non-professional investors. Due to the lack of professional skill and the complexity of financial indicators and the varying investment environment, non-professional investors are in great need of a data mining-based intelligent stock trading decision-support system. Considering the existence of concept drift phenomenon, this study proposes an adaptive learning process with the Lasso algorithm-based feature selection. Moreover, we use support vector machine as stock market predictor for stock selection and a risk-adjusted method for portfolio optimization. Finally, a web-based Adaptive Risk-adjusted Intelligent Stock Trading System (iTrade) is established. The seven-year (2005-2011) back-testing shows that our system can generate much higher cumulative return than the benchmark (Shanghai Composite Index) in China stock market. Meanwhile, concept drift analysis of adaptive relevant variable discovery process has revealed contrasting historical trends between two selected industries. In conclusion, the iTrade is suitable for non-professional investors in portfolio management, following the varying stock market environment and providing effective guidance.

E-Commerce is such a fast-growing industry that traditional teaching method is hard to meet its need of development. Based on the experience of current teaching system and the analysis of practical needs of schools, teachers, students and enterprises, Guangdong University of Foreign Studies (GDUFS) has developed 3E (E-Learning, E-Sharing, E-Creating) E-Commerce Education System (or 3E system for short), for the sake of the nurture of self-study ability, practical ability, creativity and employability. The 3E system links enterprise, school, teachers and students together. It provides a knowledge base, a bridge for communication and a practice platform of innovation, which is a great help to personnel training. When the 3E system matures, it can be applied to other universities for E-Commerce teaching.

Software project development still faces high failure rate. Nowadays, researches on software project risk majorly remain in risk theoretical model, risk identification and risk analysis, lacking empirical models which unify risk analysis and risk planning procedures. This research firstly collected real data from mainland China, and used Classification Association Rules (CARs) to provide a highly operational and planning-oriented software project risk management (SPRM) framework. Then we code programing problem, i.e. risk planning, into Constraint Satisfaction Problem (CSP), to establish a Unified Intelligent Model for Risk Analysis and Planning (UIM-SPRAP). Thus we provide a new solution to establish a framework unifying risk analysis and planning. UIM-SPRAP is the earliest model of this field, can be used to provide intelligent decision support to SPRM.

Spam, also known as unsolicited bulk email (UBE), is becoming increasingly harmful for email traffics. Filtering is a simple and efficient way to combat against spam. Machine-learning-based classification algorithms are of excellent performance in filtering spam. However, the classifiers need be trained with a group of training samples before being able to work. Heavy manual labor and privacy problems are involved in preparing these training samples. In this paper, we proposed a spam filtering system that can work without training in advance. The system is based on fuzzy clustering instead of classification algorithms, avoiding the problems brought by training samples. The system achieves reasonable filtering quality in the experiments.

Software project development is a risky process with high failure rate. This paper proposes an intelligent model that can predict and control software development risks from an overall project perspective rather than focusing only on the single factor, project output. In this study, we first constructed a formal model for risk identification, and then collected actual cases from software development companies to build a risk prediction model. In order to evaluate the performance of our model, two machine learning algorithms, Artificial Neural Networks (ANN) and Support Vector Machine (SVM), are compared. The experiments show that our risk prediction model based on SVM achieves better performance in prediction.

University students have been the most important online consumer group. Accordingly, this research intends to build up a university student behavioral intention model originally based on Technology Acceptance Model (TAM), to explore the contributing factors of intention of online shopping and their interactive relationships. We conducted sampling survey of students from Guangzhou Higher Education Mega Center, giving support to our model. The result of the model shows that perceived usefulness, perceived ease of use, perceived entertainment and perceived risk have different influence on the attitude towards using online shopping. This research is to help online vendors to better understand online consumers’ behavior and offer constructive suggestions to promote online marketing.