- QUESTION
Data Mining: Myths and Facts
In this assignment, you will explore the different truths (and lies) about data mining. Understanding the limitations and opportunities data mining provides gives you a better understanding of what you can do as an analyst or what to expect from data mining as a manager.
Tasks
Data mining has been used in analyzing data since the 1990s. The term has been surrounded by many myths and facts. Perform a search on the Internet and write a short paper listing the myths and your thoughts on why each myth is invalid (or valid). Focus on the facts that help managers make decisions and try to address myths related to decision making.
| Subject | Administration | Pages | 4 | Style | APA |
|---|
Answer
Data mining is the technique of sorting out large sets of data with the objective of identifying patterns and establishing relationships for solving problems through analysis. The process is vital in predicting future trends, generating new information and assisting managers during decision making. Adoption of data mining in enterprise dates back to the 1990s. However, despite the procedure’s effectiveness, there are particular myths about the technique and some are false while others are true as discussed in this paper.
The primary true feature of data mining is that it deals with any numbers, texts, or facts that can be computerized. In this regard, computerization involves processing the facts on a computer. Ideally, not all data sets are collected using digital formats. However, analog and physically collected facts can be inputted in a computer and processed. The approach enables data mining to apply to almost any facts. In doing so, statistical procedures such as grouping and classification are utilized. Understanding the particular type of data required for the process is crucial in helping managers make decisions. In this regard, managers will focus on evaluating organizational performance in quantitative terms for easier processing. Moreover, they will know that generating computer-friendly data hastens the decision-making process as no time will be spent converting it into digital formats.
Another fact about data mining is that it utilizes statistical knowledge in detail.
Principally, statistical analysis is useful in establishing relationships that may exist between the raw information. Usually, the grouping of facts during data mining techniques utilizes three categories: operational data, which may include organizational costs, payroll, sales, and inventory; non-operational data, which comprise forecast data and industry sales; and metadata that is essentially data relating to the collected facts. The established statistical relationship is crucial in for managers during making decisions because it indicates how the organization has performed over time and if there any possible deviations from the business’ targets. Therefore, managers can observe this and make a decision that will result in the desired change.
Data mining significantly depends on algorithms. Therefore, the argument that everything about the procedure requires highly developed algorithms is partly right. In this regard, algorithms for data analysis are vital in assessing computer information. However, other factors are also considered in mining data effectively. Therefore, better algorithms do not necessarily imply that the data mining procedure will be more efficient. Principally, data mining as a technique is made up of various components such as developing business goals, understanding data, as well as results presentation and analysis. The fact about incorporating various elements in the data mining process is vital for managers, especially when making decisions because it increases the reliability of the outcomes. As such, managers can use the data mining process results confidently knowing that the practice considered all aspects of the business.
A consistent misconception about data mining is that it requires a unique and dedicated database. In this regard, most vendors claim that one needs to have an expensive analytic server or data mart to mine raw information due to the need for pulling data into proprietary sequences for proper processing. Based on this thought, data mining becomes an expensive endeavor to start and maintain. Moreover, it becomes time-consuming. However, the actual truth is that technological advancement has made it possible to carry out data mining processes using an enterprise-wide data warehouse, which is less costly as compared to the use of distinct data marts. The impact of this discovery on decision making is that managers can decide to adopt in-house data mining teams without worrying about financial expenses involved.
The primary opportunity provided by data mining to analysts is the chance to unearth hidden information. Usually, data mining depends on available facts to evaluate trends. For instance, businesses can use the sales outcome after a particular period to understand the effect of adverts generated during that time. The approach presents an opportunity for analysts to understand the behaviors of the target population and maximize outcomes for the business. Consequently, through data mining, analysts get a chance to influence future outcomes. Data mining also presents particular challenges to analysts. Primary, the procedure involves the evaluation of personal information that may require consent before using. Moreover, matters relating to privacy and security should be managed carefully as they can result in a lousy association between businesses and their clients.
In conclusion, it is apparent that data mining is ideal for contemporary businesses. Primarily, it enables enterprises to understand their clients and evaluate industry trends. For analysts and managers, the procedure gives them a chance to predict and influence future practices while offering them data privacy and security challenges.