SUMMARY OF DATA MINING
First of all, we need to understand the difference between the data science, big data
and data analytic. Data science is when we use model, AI, or machine learning to model the
data and analyse the result. Big data is the normal collection of structured, semi-structured,
and unstructured data generated by different sources in its raw data. Besides, data analytics
provides operational insights into complex business scenarios. It is done before use data for
model or after getting the result from model. Data mining is a process to extract meaningful
information inside data using data mining technique.
Apart from that, there are various kind of data that we extract including database-
oriented data sets and applications. As example, relational database, data warehouse and
transactional database. Next, advance data sets and advance applications. As example, data
streams and sensor data, multimedia database and text database. They were also some major
issues in data mining. First is over fitting. It means when we present data too much to model.
So, they memorize the data instead of learning. Next, outliners. It means when the data is out
normal or out of range. Also, the interpretation because different human interpret the data
differently.
They were many applications of data mining. We can use data mining in almost all
kind of applications as long as the data is exist to help with decision and model the data.
These are some example of data mining application. In market analysis and management,
data mining used to explore target marketing, customer relationship management (CRM) and
market segmentation. In risk analysis and management, data mining used for forecasting and
competitive analysis. It can also be used for fraud detection a detection of unusual patterns.
