PERSONET
Personalising E-commerce using Web Mining

The aim of PERSONET is to provide training to PhD students from across Europe on "Personalising E-Commerce using Web Mining". Places will be available for three or four fellows per year for four years. Individual fellowships will be for three to twelve months in duration. A selected fellow will have the opportunity to work in a vibrant culture with opportunities to participate in theoretical training courses and gain practical skills through working with a leading research team on EU funded projects. Fellows would typically have an undergraduate or postgraduate qualification in an IT or business related discipline and be currently undertaking a postgraduate research qualification related to e-commerce.

CERENA
Developing Intelligent Personal Service Environments

The goal of CERENA is to contribute to the economic development and scientific and technological prospects of the European Community by providing market leading, value adding services to the customers of European Community banks. The objective of CERENA is to make Internet retail banking in Europe more competitive by using data mining technology to deliver services such as personalisation to the customers of the bank.

The philosophy behind CERENA is equitable relationship management, where both the bank and its customers receive mutual benefit from a trust-based business-consumer relationship. CERENA will extend and implement the latest data mining technologies, making the marketing processes in Internet retail banking supportive and adaptive to the banking needs of the customers of the banks.

NetMODEL
Representing Mined Sequences

NetMODEL’s rationale is founded on the observation that more and more commerce-related transactions are becoming digital. This is happening not just on the supplier side of the value chain, but increasingly on the consumer side. That is, new digital interactive devices are emerging in the mass-market arena. These include the Internet, Digital Interactive Television, Personal Digital Assistants (PDA) and mobile broadband telephony devices. These devices have at least one important facet in common; all the marketing channel interactions between digital service provider (information content, product and service provision) and the consumer can be recorded and stored in digital databases.

NetMODEL will investigate and develop new ways of representing information generated from data mining algorithms. Specifically NetMODEL will focus on the development of techniques for representing the output of the MiDAS (Mining Internet Data for Associative Sequences) algorithm into a machine-readable and portable form. The NetMODEL representation will be based on the eXtended Markup Language (XML), and will act as a bridge between mining and visualisation.

The overall aim of NetMODEL is to produce a test-bed system capable of representing and manipulating knowledge from different sources, including the output of the MiDAS sequence detection algorithm, information about a web site, and information about site transactions The research method will validate how XML (utilising Resource Description Framework – RDF) may be used to represent this knowledge from heterogeneous sources, and facilitate the application of that knowledge in real-time via an Internet server under HTTP

MIMIC
Mining the Internet for Marketing IntelligenCe

There are now over 80,000 on-line Internet shopping providers worldwide, with thousands more appearing each month. Each of these on-line malls generates data on the customers who use the sites to either browse or buy. The potential for direct marketing is enormous - browsers and buyers of products can be identified and targeted with attractive offers and sales promotions. The technical objective of the MIMIC project is to develop a data mining toolkit that will make possible the mining of the data generated by the malls. Data mining is the nontrivial extraction of implicit, previously unknown information from data. The output of this electronic commerce building block research will be a generic, extensible, modular software tool that transforms the customer behavioural and descriptive data into marketing information. The business objective is to provide European on-line shopping malls (of which many are SME companies) with advanced technology that will assist them in maintaining their competitiveness in the global Internet marketplace. The approach of the MIMIC project is to capture the requirements from SME on-line shopping providers, and develop specialised Internet-capable data mining algorithms. These will be validated by the users and incorporated into a special version of an existing successful data mining software tool - Clementine. A WWW site will publicise the project and show the results of the project. Exploitation will be through the SME partner who has developed and is already marketing the Clementine data mining tool. The target market segment is on-line shopping malls, and the goal of the MIMIC project is to give these malls the ability to market their products and services effectively. Such customised and directed marketing communication, however, relies on reliable and accurate information about the customer. MIMIC will provide, for the first time, the capability for malls to consider a cost-effective means of individually customised marketing communication. The anticipated industrial demand for the results of MIMIC is high. Although it is widely believed that mass marketing techniques such as advertising are a major proportion of a marketing budget, many companies now spend more on sales promotion methods, which include direct marketing techniques. The benefits of direct marketing are the ability to measure directly the response to the marketing effort, and the resultant cost-effectiveness of this technique. Direct marketing also enables on-line malls to monitor their customers behaviour patterns and to detect and entrap potential switchers - those people who show no allegiance to a particular mall. Electronic Commerce dispenses with geographic boundaries, and empowers customers to shop where they obtain the cheapest/best bargain. The marketing intelligence information from the MIMIC data mining toolkit may be used to provide a competitive edge for the on-line shopping mall, allowing them to capture, retain and satisfy customers.

GEO
Improved Forecasting of High Intensity Rainfall for Landslip Warning

The objective of the project is to improve forecasting areas in Hong Kong in which rainfall, flooding and landslide warnings have to be broadcasted at the right time and location. The available input are vast amounts of data (rainfall, wind, temperatures, etc. different atmospheric heights, as well as satellite and radar pictures), and extensive domain knowledge in the field of meteorology. To improve existing forecasting techniques a model has to be built, which can handle the mentioned heterogeneous types of data, can accept formulated domain expertise and can consider the temporal nature of the data.

IiMB
Integration In Manufacturing and Beyond

The objectives of the Integration In Manufacturing and Beyond (IIMB) Working Group are to identify outstanding key research issues, promote the take-up of research results in industry and influence European Union research policy to help create the next generation of manufacturing systems. A number of subgroups are defined having research objectives which can be derived from the overall Working Group objectives. The Working Group as a whole will support cross-fertilisation of the work of the sub-groups.

For efficient and effective communication and group work, the proposed IIMB Working Group will consist of five sub-groups. Each of the sub-groups has identified specific objectives which it will address through the exchange of research results and personnel and joint workshops. The first two sub-groups are related to the Learning Organisation whereas the last three are related to the Extended Enterprise. The mentioned sub-groups will report their findings in open conferences and international journals such as Computers in Industry.