Notes on Project

The project for the data mining course is intended to be a hand's on project. My desire is to have you experience the data mining/discovery process. Listed below are several sources of data. You may use these or other datasets which are approved by me. Software can be CrystalVision, SAS, MATLAB, S-Plus, CART or any other data mining tools you come up with. You may certainly use a combination of tools.

The project should have two parts. A written document of about 20 to 25 pages describing:

The dataset(s) you chose and its (their) basic characteristics.

The software tools you used.

The knowledge, structure, characteristics of the dataset you discovered justifying why you came to the conclusions.

In addition, you should plan on giving a presentation of approximately 15 minutes relaying to me and the rest of the class the basic information contained in your written report. The presentation should preferably be in electronic form suitable for our classroom. You may work alone or in small teams. I only require that you have your proposed dataset and proposed team preapproved by me.