For the final project you will be developing a program that uses a database to facilitate discovering useful relationships in a large dataset. Before begining on the design and implementation of the program you will need to choose languages and libraries that will best help you meet your project goals. To reduce the amount of redundant work in in this regard, the class will divide into two groups to give formal presentations, with visuals, on Non-SQL database implementations and on data mining techniques nn Tuesday, March 15th during class.
MySQL uses a client-server model of the SQL relational database that we have learned in class. This makes it great for tasks where many people will be entering information into the database, such as web site development. Your program, however, does not need to store information on a server and would therefore benefit from a different database.
But what database should you choose? That is the question that this group will help to answer. They should provide an overview different database systems including comparisons on (things) that are relavent to this project (be sure to some up with a list of features that would be important to know before choosing one of the databases.) The evaluations should include the reason the langague exists, what it is good for, and what are some of its disadvantages. (paying particular attention to the needs of your classmates for this projecgt?)
The client for the final project has a large set of data and wants to find useful or interesting relationships among the data. There are many different data minging algorithms available doing this. You will not have to code the algorithms themselves, but you will have to choose from those available to select the one best suited for your project.
What are the algorithms you have to choose from? That is the question that this group will help answer. They should provide an overview of different machine learning techniques. The evaluations should pay particular attention to advantages and disadvantages in comparison to other techniquess (ie don’t just summarize each technique, but summarize what differentiates each from the others (what does each do best or worse or not at all)
Your presentations will be evaluated as a group for content and indivdually for delivery according to the Roanoke College Roanoke College Oral Communications Rubric.