The Process of Data Mining - Case Study Example

DATA MINING Name Institution Data Mining Information can be found in almost every setting such as World Wide Web, business transactions, medical and personal data, surveillance cameras and videos and data warehouses. The data stored in these contexts can sometimes grow to large volumes, which is difficult for individuals to analyze and make reports on them. However, with the assistance of data mining tools, it is now possible for organizations and companies to analyze such data with an effort of establishing favorable patterns that suit them. Therefore, data mining refers to the process of compiling and extracting information usually considered potentially useful from large data volumes. Data mining enables the products to meet the needs and desire of the consumer, and at the same time rake in profits companies. In addition to these, companies are able to properly organize the strategies they are going to employ in the development of a particular product. Consequently, reducing the cost of production while at the same time increasing the rate of production and the profit accrued (Marban et al 2009, p. 88). Therefore, some of the benefits attained as a result of using data mining are: Demand forecasting Most companies are driven by demands of their products, but in order to ascertain this demand is beneficial they conduct research on the consumers. These research help the companies determine whether the demand necessitates the production of a particular product and whether the product likely to rake in profits. Despite this knowledge, companies have experienced difficulties in analyzing reports from these research, but with the help of data mining they are able to analyze report regarding demand. By looking and interpreting information from large data sets with the help of data mining tools, they are able to establish reports that touch on demand of their products. For example during, business transactions, a lot of information is exchanged and some of them may go unnoticed. However, with the help of data mining it is possible to retrieve such information which could prove vital for growth of a company. Therefore, companies are able to make informed decision on production of a particular product, thus reducing chances of suffering losses. Data mining also, enables companies to predict the life span of their products and the probable changes to be experienced in the future (Cotino et al 2003, p.220) Product development Products always reflect the needs and desires of the consumer, meaning that they should have features that are appealing to the consumer while at the same time allowing the consumer to achieve their objectives. However, meeting the needs of consumers has proven challenging especially when dealing with a large based consumers. Data mining on the other hand makes this a possibility since companies can establish desires and needs of consumers. Therefore, companies are able to develop products that incorporated the desired features of the consumers while at the same time enabling companies to realize profits from their products. In conclusion, data mining allows companies to meet the needs and desire of the consumers (Kumar, 2004) Overcoming competition It is common knowledge that there will always be competition among companies for the attention of the consumers. This competition is essential as it ensures that the products are of high quality and meet the objectives they were created to accomplish. However, for a company to have an edge over their rival companies they have incorporated the use data mining in the development process of their products. Data mining provides reports that indicate the features present in their rival products while at the same time illustrating some of the features that they would want to see in their products. With these information companies are; therefore, able to incorporate some of the features in the development of their products. This gives companies an edge over their rival companies while at the same time meeting the needs of their consumers (Kumar, 2004) Marketing feedback Sometimes companies incur a lot of expenses in conducting advertisement of their products. However, it becomes difficult to establish whether the advertisement have any impact on marketing their product. In such instances data mining comes in handy, as it provides feedback to the companies on how consumers accept their products (Hand & Smyth 2001, p. 200) Implementation issues As a result of the various benefits associated with the use of data mining, most companies have gone further to adopt it in their development process of some of their products. However, the use and adoption of data mining by companies has not come in easy but has witnessed certain challenges that hinder its implementation by most companies. Data mining tools are mostly technologically based products, and are, therefore, exposed to numerous risks that make it difficult for companies to realize their benefits (Yang et al 2007, p. 597). Some of the challenges and risks likely to be experienced during data mining include: Attacks Since data mining involves extraction of information from various sources, data mining tools become susceptible to attacks. These attacks come in the form of viruses, spams, Trojans and malware. They are normally configured to cause harm to computers or computer based programs such as data mining tools. Data mining tools generally do not have the ability to sieve out these attacks and once they are opened they could cause harm to the programs. In addition to these, these attacks also corrupt the report prepared by data mining tools, and if companies use these reports in implementing their decision they could suffer huge losses. This is because reports are manipulated and do not represent the real situation on the ground, companies might end up making huge losses. It is therefore necessary to ensure that the program is attack free (Yang et al 2007, p. 600) Cost The adoption and use of data mining tools to analyze data has also come under scrutiny due the cost companies incur while using them. This is because; companies willing to data mining tools have to incur the cost of installation and maintenance. This can prove challenging to companies who do not have enough financial resources to meet such requirements (Yang et al 2007, p. 602) Validity of data Sometimes it is difficult to prove the validity of data used in the extraction of information by data mining tools. This can be attributed to, the fact that data is collected from different sources and some of the data might not relate to a company or does not depict the position of the society. Also, data mining tools do not have the ability to integrate the ever evolving data, especially in the business world makes it difficult to prove the validity of such information. Data mining tools should therefore be developed in a manner that integrates evolving data to improve validity of reports (Yang et al 2007, p. 603). Technicality The use of data mining is also limited to leaned members of an organization, because it reports produced by data mining tools could prove challenging in interpretation by other members of a company. Therefore, application of data mining is limited to university graduates who have acquired knowledge from their studies and are therefore able to better interpret information presented to them. Also, the fact that data mining tools are recent technological advancement it might be difficult for people who do not have technological knowledge. (Yang et al 2007, p. 603) Privacy and security issues The process of data mining involves extraction and interpretation of personal information, and this has raised many concerns. This is mainly because individuals do not have control of what happens to the information retrieved or which persons have access to such information. It is also a concern among individuals as to how the information will be used. (Yang et al 2007, p. 604) References Cotino, A.S., Gutierrez, J.M., Jakubiak, B. & Melonek, M. (2003). Implementation of data mining techniques for metrological applications, World Scientific, 215-240. Hand, D., Manilla, H. & Smyth, P. (2001) Principles of Data Mining. Massachusetts: MIT Press. Kumar, S.T. (2004). Introduction to Data Mining [Pdf document]. Retrieved from www-users.cs.umn.edu/~kumar/dmbook/dmslides/chap1_intro.pdf Marban, O., Segoria, J., Mensalvas, E. & Fernandez-Baizan, C. (2009). Toward Data Mining Engineering: a Software Engineering Approach. Information System, 34 (1), 7-107. Yang, Q. & Wu, X. (2007). 10 Challenging Problems in Data Mining Research. International Journal of Information Technology, 3 (4), 397-604. Read More