The importance of the electronic real estate ads increases day by day, it is attested by the huge number of ads on the internet. The processing of this data creates excellent opportunities, at the same time it is a significant challenge. In this thesis I’ll implement an application, what enables us to explore real estate market trends. The other main goal of the application is to predict the prices of the properties.
The application consist of three main components. The first one is responsible for the collection and persistent storage of the real estate ads. This component is based on an application previously created by an other student. I improved and automated this solution. The second component contains the required features to present the trends. Finally, the last component is responsible for the predictive models.
The business logic of the services has been created using a data mining tool, called RapidMiner, and the user interface is a simple server side application written in Java.