According to Chen and Ordonez in their article “Horizontal Aggregations in SQL to Prepare Data Sets for Data Mining Analysis, there has been difficulty in the past preparing database information for data mining. Data mining usually uses aggregate information to start the mining process. With SQL the data that is derived from the query in aggregate form is usually in a vertical view. They give detailed information in their paper explaining how to evaluate and optimize horizontal aggregations of data. Some of the benefits of doing this process in the database itself are to reduce manual work in data Right preparation and data security.
Although, I don’t understand the inner workings of their function being new to SQL but I can tell that the information provided is a valuable tool for processing information in data mining. If I ever find myself as a database administrator or programmer, I will certainly take a closer look at their paper. Any company can save money if the data mining preparation is time-consuming.
The more I review the wealth of information in the library the happier I get. When I find a job, I will be sure to utilize the databases in the library to gain more knowledge. Maybe it will help me get a raise.
Chen Z. & Ordonez C. (April 2012). Horizontal Aggregations in SQL to Prepare
Data Sets for Data Mining Analysis. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 24 NO. 4, 678-691. doi::1109/TKDE.2011.16