Data Mining, Research Paper Example

Data mining is a process attempting to make discoveries of patterns in large data sets. It does automate sensing of appropriate patterns available in a database. Data mining usually utilizes available methods at the intersection of database systems, machine learning, statistics, and artificial intelligence. Data mining process plays a significant role in extracting significant information from data set, then using its patterns transforms this information into a structure that can easily be understood for further use and functioning. Data management does not only involve raw analysis step, but it also several aspects. These aspects include online updating, complexity considerations, and model and interference considerations. It is important to note that data mining enhances post-processing of discovered structures, data processing, and data management processes (Pyle, 2003).

Data mining process involves automatic or semi-automatic analysis whereby large quantities of data are involved. These data usually extracted from patterns of data records and analysis such as association rule mining, anomaly detection and cluster analysis. All these analysis utilizes spatial indexes as an appropriate database technique. The process usually involves searching, cleaning, collecting, and analyzing data from different database sources with the sole purpose of evaluating them. The process can thus be said to be an automatic analysis of files found in online for the purposes of discovering patterns, which could have gone undiscovered and unexplored. Data mining involve several classes of tasks these include anomaly detection, association rule learning, classification, regression, clustering and summarization. Each of these classes is of significance in ensuring that the businesses or organization’s data and operations and handled appropriately.

Data mining algorithms comes after assembling of target data. Assembling is possible in situations where the target data is large and capable of containing the appropriate patterns and at the same time capable of being mined within the given time. Smart mart or data warehouse is usually the common source of data mining (Pyle, 2003). After data assembling has been done, the target data undergo cleaning where those observations, which contain noise, are normally removed and the ones with mining data set aside.

Data mining is technological advancement, which has resulted from the emergence of the IT industry and economic development. In this regards, data mining has now become a popular process. Several companies in the recent years are in need of solutions provided by data mining since it provides them with advantage over its competitors. With the aid of data mining, several companies have managed to gather data from various sources. This has increased benefits to the company in ensuring that efficiency is achieved. Business intelligence data mining have come up with the help of data mining, which involves gathering meaningful data from several sources especially online podiums. This is done with an intention of reaching at a sensitive business decisions (Pyle, 2003). This process usually includes economic trends, industry research, competitor and competition analysis, geographical information and market, and economic trends. With the help of data mining, various organizations and businesses have been able to manage their competitors.

Data mining helps companies and business entities in discovering information concerning their customers and the behavior of these customers towards products. In this regard, the businesses entities can then analyze, evaluate, store and synthesize crucial information from data related to the customers. Thus, data mining is a significant tool for organizations in enabling them makes improvements concerning their marketing strategies and provision of appropriate analysis concerning their customers.

The process has been of considerable help to organizations in providing solid customer focus this is because of its flexibility in its application and in foreseeing crucial data, which include customer-buying behavior, in addition to industry analysis.

Data mining process is a reliable process in undertaking business processes. It is one of the steps taking place between a business or a company and its customers. The influence on data mining on business is dependent on the processes of the business and not the process of data mining. Data mining results are usually distinct from those of other business processes, which are usually data-driven. Analysis of customer’s data using data mining shows that the results the user gets are the information known to them; and that they already existed in the database. Data mining has enabled businesses selling its products indifferent regions to translate easily the display of the information found to an appropriate understanding concerning various business processes.

The process is valid in that it extracts hidden information from the database, the user concerning its existence might not know some information. It has also aided in finding the relationship and connection between the customer’s behavior and different variables, which are normally non-intuitive. The advantage of data mining in this case is that it can utilize the output of its system after translating into solutions for business problems thus benefiting the business entity. Data mining has been a reliable process since its output has enabled the company to find the list of target customers and thus increasing their credit limit. The persons concern, in the process, has little task to accomplish since all the tasks has been accomplished by the data mining process, this has proved to be an effective approach and an efficient one thus affordable to any other business.

However, using results from data mining has proved to be a difficult means in using its results and getting the customers understand the process effectively and to take action in its operations. These processes can be of considerable benefit to customers in cases where the data mining system is made clear to the customers so that they can understand it qualitatively. It is imperative that failure to do so renders the process inappropriate (Kudyba & Hoptroff, 2001).

Assessing the reliability of this process can be achieved using several approaches. These methods include measuring statistical validity with the aim of determining where the problem are found. It involves separating data into training and testing its prediction accuracy and viewing the results with an effort of determining the meaningfulness of the discovered patterns. Utilizing all these methods leads to the effectiveness in using data mining process. Data mining can only trusted in situations where the company has effectively put in place the appropriate approaches in assessing the information found using this process. The process is, however, unreliable in cases where the extraction of information is extracted from the customer’s hidden behaviors and understanding these processes becomes complicated.

Data mining’s paramount concern is privacy. The technology of data mining is prone to abuse by different parties. For example, when one fills information in bank during loan processing, all the personal information is normally left in a database and are normally assessed by anyone (Soares & Ghani, 2010). This has led to cases of insecurities since thugs and robbers in tracing the person can use personal private information. Data mining usually make an assumption concerning the location of the information; they assume that the information in databases is held in one location within the organization. This, however, is not the case since information in the organizational database can fall in the hands of those who assess the database within and outside the organization, implying that private information are made public, and anyone can access in the internet thus privacy policy violated.

Privacy concern and legal issues in data mining are the leading source of conflict in business entities. In the recent past, government and corporate entities collect data and stored in data warehouses thus placing the privacy of consumers in a jeopardy state.

Consumers have, however, raised some privacy concern these include Secondary Use of the Personal Information, Handling Misinformation, Granulated Access to Personal Information and new privacy threats. The substantial privacy concern facing consumers is the use of private information, government and business entities normally access the information of the customers obtained from the organizational database and use it for other purposes mainly for their own benefits. This poses a problem in the side of consumers since their privacy is tampered with without relevant consultation. This concern is valid for consumers to raise since their privacy is interfered with and crucial information are left in the hands of strangers hence their security interfered (Shmueli et al, 2011).

Handling of misinformation by other parties who get access to customers’ private information in the company’s database, is also an ethical issue related to data mining. This information are usually prune to mishandling by the third party making the whole thing irrelevant. The consumers concern is valid since their personal information can be tampered in the hands of other internet users. New privacy threats as a privacy concern raised by the consumers, the threat is normally posed by Knowledge Discovery and Data Mining (KDDM), have lead to consumers information being interfered with. The threat normally includes deductive learning, data collection, and statistical analysis. This poses the problem to privacy of consumers since there is no guarantee of personal information being secure. The concern is valid since if left, personal information can get into the hands of individuals who are not trustworthy.

References

Kudyba, S. & Hoptroff, R. (2001). Data Mining and Business Intelligence: A Guide to Productivity. Idea Group Inc (IGI).

Pyle, D. (2003). Business Modeling and Data Mining. Morgan Kaufmann.

Shmueli, G., Patel, N., & Bruce, P. (2011). Data Mining for Business Intelligence: Concepts, Techniques, and Applications in Microsoft Office Excel with XLMiner. John Wiley & Sons.

Soares, C. & Ghani, R. (2010). Data Mining for Business Applications: Frontiers in Artificial Intelligence and Applications. IOS Press.