International Journal of Information Technology & Decision Making

From 1978 to 2004, China's GDP growth rate has been 9.4% annually. In 2005, China's GDP growth rate was 9.9%, which at $2,278 billion currently is ranked number four in the world. This paper discusses the significance of transforming research findings in data mining and knowledge management (DMKM) to support China's economic development as well as the trend of DMKM applications in China. It first reviews development of DTKM in international communities and industries, which includes academic activities and business applications tools. Second, this paper outlines the significance and needs of DTKM in China's economic development, as to promote further DMKM research, innovatively produce new business intelligence tools, and effectively adopt existing commercial software packages. Finally, the paper observes some problems and challenges of using DMKM to support China's economy.

In October 2005, we took an initiative to identify 10 challenging problems in data mining research, by consulting some of the most active researchers in data mining and machine learning for their opinions on what are considered important and worthy topics for future research in data mining. We hope their insights will inspire new research efforts, and give young researchers (including PhD students) a high-level guideline as to where the hot problems are located in data mining.

Due to the limited amount of time, we were only able to send out our survey requests to the organizers of the IEEE ICDM and ACM KDD conferences, and we received an overwhelming response. We are very grateful for the contributions provided by these researchers despite their busy schedules. This short article serves to summarize the 10 most challenging problems of the 14 responses we have received from this survey. The order of the listing does not reflect their level of importance.

In recent years modern methods of optimization have contributed greatly to the advances in data mining and related areas. These contributions continue today and promise to further advance the state of the art both in terms of modeling innovations and new solution methodologies. In this paper, we present a new modeling and solution methodology for unsupervised clustering. Preliminary computational experience is given to illustrate the approach. This methodology is part of our current research and offers considerable opportunity for additional investigation to be conducted by other researchers.

The paper is devoted to a visualization-based method for exploration of relational databases that contain large volumes of uncertain data. The visualization is aimed at exploration of properties of the data and selecting a small number of interesting items from the database. The method introduced here is a new development of the Reasonable Goals method, which has already been implemented on Internet in the form of the Web application server. Thus, the new method can be applied on Internet, too. It can be used for selection-aimed data mining in various fields including environmental planning, machinery design, financial planning (including credit operations), biology and medicine.

In this paper, we give a brief summary of the author's recent attempts conducted in collaboration with a number of co-authors to deal with uncertainty in various optimization problems, including complementarity problem, mathematical program with equilibrium constraints, as well as applications in data mining, mathematical finance, and game theory.

In this paper, we develop a new constrained artificial-neural-network (ANN) formulation and the associated learning algorithm for predicting stock prices, a difficult time-series prediction problem. We characterize daily stock prices as a noisy non-stationary time series and identify its predictable low-frequency components. Using a recurrent finite-impulse-response ANN, we formulate the learning problem as a constrained optimization problem, develop constraints for incorporating cross validations, and solve the learning problem using algorithms based on the theory of extended saddle points for nonlinear constrained optimization. Finally, we illustrate our prediction results on ten stock-price time series. Our main contributions in this paper are the channel-specific low-pass filtering of noisy time series obtained by wavelet decomposition, the transformation of the low-pass signals to improve their stationarity, and the incorporation of constraints on cross validation that can improve the accuracy of predictions. Our experimental results demonstrate good prediction accuracy and annual returns.

Data stream mining has attracted considerable attention over the past few years owing to the significance of its applications. Streaming data is often evolving over time. Capturing changes could be used for detecting an event or a phenomenon in various applications. Weather conditions, economical changes, astronomical, and scientific phenomena are among a wide range of applications. Because of the high volume and speed of data streams, it is computationally hard to capture these changes from raw data in real-time. In this paper, we propose a novel algorithm that we term as STREAM-DETECT to capture these changes in data stream distribution and/or domain using clustering result deviation. STREAM-DETECT is followed by a process of offline classification CHANGE-CLASS. This classification is concerned with the association of the history of change characteristics with the observed event or phenomenon. Experimental results show the efficiency of the proposed framework in both detecting the changes and classification accuracy.

We propose a new finite element surface fitting method which can handle very large databases. This method uses finite element discretization to find an approximation of a smooth function which minimizes a sum of data residuals and second derivatives under some constraints on data. The finite element discretization derives a large scale constrained quadratic program, which can be reformulated as a system of piecewise linear equations. We develop a preconditioned Newton method to solve the system efficiently. We apply this method to form surfaces over Aomori Region in Japan by geographic databases, such that every bridge became associated with environmental information.

Customized goods and services occur when their respective supply and demand chains are managed in a simultaneous and real-time manner. From a research perspective, we classify the methods that are employed in the management of these chains, based on whether supply and/or demand are flexible or fixed. Interestingly, our classification scheme highlights a critical and rewarding research area at which both supply and demand are flexible, thus manageable. Simultaneous management of supply and demand chains sets the stage for mass customization which is concerned with meeting the needs of an individualized customer market. Simultaneous and real-time management of supply and demand chains, in turn, set the stage for real-time mass customization (e.g. wherein a tailor first laser scans an individual's upper torso and then delivers a uniquely fitted jacket within a reasonable period, while the individual is waiting). The benefits of real-time mass customization cannot be over-stated as products and services become indistinguishable and are co-produced in real-time, resulting in an overwhelming economic advantage. Customized goods and services can only be achieved through sophisticated data mining techniques that can define the customization requirements from both a supply and a demand chain perspective, techniques that can obtain pertinent information from the mass of non-homogeneous data, in order to make informed customization decisions.

This composite paper focuses on the Service Sector and its growing importance. Some of the characterizations made of the Service Sector using a simple analysis of data bases derived elsewhere are indicated. Discussion of the distinction between the role of intellectual property in the Goods Sector and the Service Sector is made.

Knowledge economy requires data mining be more goal-oriented so that more tangible results can be produced. This requirement implies that the semantics of the data should be incorporated into the mining process. Data mining is ready to deal with this challenge because recent developments in data mining have shown an increasing interest on mining of complex data (as exemplified by graph mining, text mining, etc.). By incorporating the relationships of the data along with the data itself (rather than focusing on the data alone), complex data injects semantics into the mining process, thus enhancing the potential of making better contribution to knowledge economy. Since the relationships between the data reveal certain behavioral aspects underlying the plain data, this shift of mining from simple data to complex data signals a fundamental change to a new stage in the research and practice of knowledge discovery, which can be termed as behavior mining. Behavior mining also has the potential of unifying some other recent activities in data mining. We discuss important aspects on behavior mining, and discuss its implications for the future of data mining.

Web Intelligence (WI)-based portal techniques (e.g. the wisdom Web, data mining, multi-agent, and data/knowledge grids) will provide a new powerful platform for Brain Sciences. New understanding and discovery of the human intelligence models in Brain Sciences (e.g. cognitive science, neuroscience, brain informatics) will yield new WI research and development. In this paper, we briefly investigate three high-impact research issues as well as present a case study, to demonstrate the potentials of Brain Informatics (BI) research from WI perspective.

We usually use a set of ideas, thinking paradigms and judgment rules, including alternatives, criteria, outcomes, preferences, to make decision. This set, known as actual domain (working knowledge) of habitual domain, will be stabilized over time unless extraordinary events occur. As such, our working knowledge cannot be broad and deep. Inevitably, we could get into decision traps, which lead us to making wrong decision or solving wrong problems. The actual domain is only a small part of our potential domain, the collection of all thoughts, ideas, thinking paradigms, etc. that have ever been encoded in our brain. In this paper, we will describe nine principles for deep knowledge, so that, we could expand and enrich our working knowledge by utilizing the potential domains of ourselves and other participants in the decision making. As a consequence, good ideas for solving challenging decision problems can be obtained or created. These principles are: The deep and down principle, the alternating principle, the contrasting and complementing principle, the revolving and cycling principle, the inner connection principle, the changing and transforming principle, the contradiction principle, the cracking and ripping principle, the void principle.

To solve or resolve public policy problems requires decisions. The intent is to choose the best alternative in each situation. Hence, the way the notion of best is defined and measured in each case is critical. A structured process is outlined to acquire knowledge about public values that could be used to evaluate alternatives and identify the best ones. These values are the foundation for any policy decision. The uses of these values for defining interest in the problem, creating alternatives, and identifying information needs are discussed. Research needs are outlined.

In this paper from the Xiangshang Forum 2006, we propose the Wisdom project, an international network initiative on developing the next generation of management and entrepreneurial systems based on knowledge and wisdom rather than data and information. This is a major challenge especially for China which must aspire to become wise and ethical rather than just efficient or effective. Major topics of the project include knowledge management, wisdom systems, added value measures, entrepreneurial university, and management as a profession. These topics are the key ones for developing sustainable competitive advantage of any globally aspiring economy or enterprise.