Making Sense of Data: A Practical Guide to Exploratory Data Analysis and Data Mining

2.5 PROJECT PLAN

The extent of any project plan depends on the size and scope of the project. However, it is always a good idea to put together a plan. It should define the problem, the proposed deliverables along with the team who will execute the analysis, as described above. In addition, the current situation should be assessed. For example, are there constraints on the personnel that can work on the project or are there hardware and software limitations that need to be taken into account? The sources and locations of the data to be used should be identified. Any issues, such as privacy or legal issues, related to using the data should be listed. For example, a data set containing personal information on customers’ shopping habits could be used in a data mining project. However, information that relates directly to any individual cannot be presented as results.

A timetable of events should be put together that includes the preparation, implementation, and deployment steps. It is very important to spend the appropriate amount of time getting the data ready for analysis, since the quality of the data ultimately determines the quality of the analysis results. Often this step is the most time-consuming, with many unexpected problems with the data coming to the surface. On the basis of an initial evaluation of the problem, a preliminary implementation plan should be put together. Time should be set aside for iteration of activities as the solution is optimized. The resources needed ...