Data Mining Report: History, Applications, and Techniques

This report provides a comprehensive overview of data mining, starting with its historical evolution and tracing its development from early statistical methods to modern applications. It details the core concepts of data mining, emphasizing its role in transforming raw data into valuable information for decision-making processes across various industries. The report discusses key applications such as classification, association, time series analysis, and clustering, highlighting their significance in business intelligence and strategic planning. Furthermore, it references significant milestones, including the contributions of key figures and the emergence of data mining as a distinct field. The conclusion underscores the impact of data mining techniques in enabling businesses to make informed predictions, optimize operations, and increase revenues in a knowledge-driven society.

Running Head: DATA MINING 1
Statistics
Institution Name
Student Name
Date of Submission

DATA MINING 2
Introduction
Data mining is evaluation of invisible patterns of data according to variety of concepts of
grouping into useful information, which is gathered and combined in common areas, such as data
warehouses, for convenient analysis, algorithms of data mining, enhancing making of decisions
in business and other information necessities to ultimately minimize costs and increase revenue.
There is a lot of information found in information industry. The data is valueless if it is not
turned into productive information. It is important to evaluate the large quantity of data and
obtain productive information from it. Apart from being used to extract information, data mining
also involve other activities like data cleaning, translation, integration, evaluation and date
presentation. After carrying out all of the processes, the information can now be used to carry out
practices such as management of production, inspection of fraud, studies of science and
evaluation of market. (Simbarashe, 2011).
Despite the fact that Data mining is usually associated with the new technology. It is
however a subject with a long history. In 1763, Thomas Bayer’s paper was published and it
introduced Baye’s theorem which is significant in probability and data mining. In 1805, Adrien-
Marie Legendre and Carl Friedrich Gauss used knowledge of regression to investigate the orbits
of about the sun. In 1943, Walter Pitts and Wareen McCulloch generated a notional model of a
neuron network which can be used to obtain and process input then produce output.
Fig: Evolution of data mining

DATA MINING 3
Source: https://hackerbits.com/data/history-of-data-mining/
John Henry Holland wrote a book “Adaptation in Natural and Artificial Systems” in 1975
which execute field study, exploring applications, presenting the theoretical foundations. In
1990, the term “Data Mining” emerged in the database system. In 1992, Isabelle M. Guyon,
Bernhard E. Boser and Viadimir N. Vapnik proposed an advancement on the initial support
vector machine which enables the generation of nonlinear classifiers. Even though the term data
science was there since 1960s, William S.Cleavel introduced it independently in 2001. (Ray,
2015).
Today, data mining is being applied in engineering, business, science and other entities.
Applying the information that is present in a data warehouse, data mining can answer the queries
that the person making decision would not ask unless he/she had those tools. Some applications
of business decision making processes include classification which finds rules to dictate if an
item or event belongs to investigated subset of data (the WriterPass journal, 2012). Associations
which constitutes methods such as linkage analysis which is used to determine the patterns of
operational transactions with high chances of repetition, as it occurs when evaluating a basket in
the search of the same products. For example, a wholesaler could want information about the
buying behaviours of his/her customers to place the products usually bought together or offer
promotions. Time series analysis which is linked to sequence is used to relate time to activities,
for example, due to this model a decision maker can know that a fridge if often purchased after
determined previous purchase. Clustering methods can be applied to simplify the parameters of a
group of data. Therefore, clustering methods can be applied to generate partitions so as to put
similar products together (Jagtap, Fadewar, & Shinde, 2011).
Conclusion
In the knowledge society, business people compete to improve their operations and increase
their revenues. Access to knowledge and technology makes it possible for everyone to improve
the performance of their organizations. Data mining techniques have greatly influenced changes
in business by enabling business people to make proper predictions thus coming up with right
decisions.

DATA MINING 4
Reference
Jagtap, S., Fadewar, H., & Shinde, G. (2011). Knowledge and Data Mining in Decision Making
Process: A Business Model. Internationa Journal of Paralle and Distribute Systems, 1(1),
1-4.
Ray, L. (2015). History of data mining. Retrieved from hacker bits:
https://hackerbits.com/data/history-of-data-mining/
Simbarashe, C. (2011). Data Mining . Retrieved from http://www.courses.co.za/users/admin
the WriterPass journal. (2012). How is data mining applied to decision making? Retrieved from
the WriterPass journal: https://writepass.com/journal/2012/12/a-review-of-how-data-
mining-is-applied-to-decision-making/