To propose an efficient CRM-data mining framework for the prediction of customer behaviour in the domain of banking applications. Within the framework proposed, two classification models are studied and evaluated.
The system is divided into three types of intelligent agents: a “master”, a “crawler” and a specialised “extractor” that is constructed according to the site that is subject to data scraping. The implemented intelligent agents framework allows Australian NDIS and Aged Care Service providers to onsale the cloud based system to other organisations in the Aged Care industry.
The Master/Crawler cooperate to the scheduling job ig database of fetching of data from a presented URL. They were made separate so has to be able to have several fetching agents (crawlers) and to be able to make them anonimate if necessary. This is sometimes a requirement that depends on the amount of data to be extracted and how paranoid the external sites are to automatic non-human browsing. Based on this they can block access. The master agent (we are assuming that only one is necessary) acts as a maestro that is responsible for distributing URL’s to be fetched by the crawler community.
Building a simple a user friendly web-based data mining tool reducing the amount of time need for decision making phase and increase the productivity of decision makers since it requires only a web browser. Using Intelligent Agents for the My Aged Care Portal to collect useful data: These agents use information retrieval techniques and characteristics of open hypertext Web documents to automatically retrieve, filter, and categorise them. Intelligent Agents developed as a Firefox plugin and based on the Mozilla WebExtensions API to collect the right data of the Aged Care portal and later on other Internet resources. The My Aged Care portal, the primary platform mined by the agents includes individual pages, PDF data, Mining Data Records and can be used to group, categorise, analyse, and retrieve documents of your clients in the portal.