Data Mining
After the Internet, digital mining has become a new research hot spot,
especially for large-scale and large-scale distributed digital mining, which
has a broader outlook and potential economic value of it is also unlimited.
Among them, classification prediction technology will help future smart
business operations and make important benchmark decisions. According to
Seidman (2001), "Data mining is of particular value to organizations that
collect large amounts of historical information. This technology is used by banks,
insurance companies, and credit card companies to extract important
information” (p. 6). “Web (data) mining
refers to a collection of data mining and related technologies used to
automatically discover and extract information from web documents and
services. of personal data, it helps
companies build detailed customer profiles and extract marketing intelligence”
(Wel, 2004). One of the most well-known uses of data mining is in the financial
sector. Individual credit risk assessments performed by banks are used to
determine whether an applicant represents appropriate 'risk'. When loan
applications are filled by the loan applicants, they are required to give
addresses, social security numbers and other information which can identify
them. In addition, they must also provide other information that says something
about them. You will be asked about the duration, marital status, education
level, etc. If the bank requires all this information, it analyses the data
received and discovers the relationship between the applicant's personal
characteristics and the likelihood of defaulting on the loan. The data mining process is mainly
divided into three steps:
1.Pre-processing: Gather relevant data in large quantities.
2.Mining: Data classification, clustering, error correction, and
information linking.
3.Verification: Confidence in new information.
Data mining is used successfully by
many companies. This technology is suitable for any company that wants to
better manage customer relationships with a large data warehouse.
Information-intensive industries such as financial services and direct
marketing are typically the first to adopt this technology. There are two key
elements to successful data mining.
- Large, well-integrated data warehouse
- Clear understanding of the business processes data mining is applied
to
Successful companies: shipping companies, pharmaceutical companies,
credit card companies.
Today, more and more companies and
organizations implement data mining techniques, but a complete and clean plan
must be made for the entire process of data definition, data collection,
storage, mining and analysis. It is important. that. In addition, “information quality” must be
considered at every stage throughout the process. In other words, before data
is prepared and extracted, the quality of information should be checked. Data
should be checked for completeness, correctness and correctness Data mining
shows the need for data validation, cleaning and validation techniques. It can
give a step-by-step overview of the relationship between a customers and the
company, or between products and services. This can trigger a completely
different parsing path. And all these efforts will enable the organisation to
do its own intelligence and knowledge discovery so that future mining efforts
are also better supported. Otherwise, they will fail or the data they receive
will not provide the values they want, and this will not allow them to make
real decisions.
References
Buczak and E. Guven,
“A survey of data mining and machine learning methods for cyber security
intrusion detection,” IEEE Communications Surveys & Tutorials, vol. 18, no.
2, pp. 1153–1176, 2017. View at: Publisher Site | Google Scholar
R. Delmaster, and M. Hancock (2001). Data Mining Explained. Boston:
Digital Press.
Comments
Post a Comment