An Oracle SQL developer/analyst can become a satisfactory data miner if she learns to know a PL/SQL procedure and a SQL function:
1. A PL/SQL procedure create_model in dbms_data_mining package.
2. A SQL function prediction_probability.
A good thing is that learning the above items is within the framework of Oracle PL/SQL. There is no need to study another special data mining/statistical language such as SAS or R. There is no need to install another standalone data mining software. Everything happens within the database using PL/SQL or SQL that she is already familiar with. Thus it is possible that an Oracle SQL developer/analyst becomes a very productive data miner. As the majority of enterprise data existing in the databases, SQL programmers have the advantage over SAS or R programmers in that she is closer to the data. If we consider data mining as just more sophisticated SQL queries, data mining is simply a natural extension of SQL programmer/analyst's daily job, i.e., querying the database.
Tuesday, September 04, 2012
How easy is it for a SQL developer/analyst to become a data miner?
Subscribe to: Post Comments (Atom)
Post a Comment