Knowledge Management Essay
Knowledge management has become a very popular concept in the last decades. Knowledge management has become very important for organizations and is considered as a significant element in their success. Generally, knowledge management is made up of different processes which include creating knowledge, transmitting knowledge, storing knowledge and retrieving knowledge. Knowledge management is defined by Nielson (2001) as a discipline that is based on the commitment to identify, capture, retrieve, share and evaluate the knowledge resources of the organization. It basically revolves around two themes – acquisition and dissemination of knowledge in the organization and the use of knowledge in achieving a competitive advantage (Lengnick-Hall, 2002, p. 85). Knowledge management systems are intended to aid the organization by giving a framework together with various devices and strategies to reuse gathered intellectual resources. Knowledge management systems are useful because they enable the organization to tap a large pool of knowledge and information as challenges and opportunities arise. Knowledge management systems, therefore, increase the responsiveness of the organization in every situation (Thierauf, 2001). The core components of knowledge management, according to Thierauf (2001) “are knowledge discovery, knowledge organization and knowledge sharing” (p. 97).
This paper discusses one of the most interesting elements of knowledge management which is data mining. Data mining is of great interest to the writer because of its contribution to the success of the knowledge management system and its potential as a contributor to the success of the organization. Data mining is defined as a knowledge management system which focuses on knowledge discovery. Data mining aids in the analysis of data. Through data mining, users can examine data from various standpoints and allow to summarize them into useful information. Data mining is seen as a process that offers several benefits to organizations. Data mining according to Chopoorian et al. (2001) enables the extraction of hidden predictive information from large databases. Data mining is a strong approach which has a big potential to aid the organization in focusing on the most essential information that can be found in its databases. There are two steps in data mining according to Chopoorian et al. (2001) – warehousing and mining.
Warehousing makes up the majority of the whole data mining process. Warehousing is the process of collecting data from various sources and of different formats, making them available for users for decision-making. Warehousing requires systems and technologies that will combine data from different sources, create a uniform format and store them for reusing.
Mining is the process of extracting information automatically from massive databases or warehouses. Mining employs different techniques in automated searching of patterns in a database. There are four general types of analysis that are used in mining. These are standard query reporting, online analytical processing (OLAP), statistical analysis, and knowledge discovery (Saarenvirta, 1999).
Importance of Data Mining
Data mining is used to search for valuable information from a large repository of data collected over time, which could be used in decision-making (Keating, 2008). Data mining is essentially a process of analyzing data and information within a multidimensional framework. This system allows users to retrieve data that they can use within or even outside the organization. Data mining products offer a basic analysis capability and the ability to drill down to obtain more detail and summarize details as necessary (Thierauf, 2001). Interest in data mining is increasing as organizations seek to better understand their business, to better serve their customers, and to better understand their business, to better serve their customers, and to increase their effectiveness. Data mining enables the extraction of hidden predictive information from large databases. It is a powerful approach with great potential to help organizations focus on the most important information available in their existing databases. It provides tools to predict future trends and behaviors and to allow managers to make proactive, knowledge-driven decisions (Chopoorian et al, 2001).
Data mining has a very big potential to be a helpful knowledge management system for organizations. Through data mining, organizations are able to access and retrieve valuable data within the organization and from a variety of sources. This can help the organization gain insights about the business, the customers, the market and the industry. Data mining has a number of uses, many organization uses data mining in several applications such as in consumer research and marketing, analyzing products, forecasting the supply and demand, e-commerce, investment trend in stocks and real estates, telecommunications and many others. The success of organizations today depends on the ability of organizations to quickly and effectively convert data into comprehensible information. The ability to share and use data is considered as a competitive advantage. Data mining has evolved from a simple concept of Business Intelligence to a significant source of competitive advantage. Data mining offers a way for organizations to gather data and information that can be used for competition analysis, researching about the market, trends in economy, behavior of the consumers, researching about the industry. So, business intelligence is vital in decision-making.
Data Mining Process
In 1996, the Cross-Industry Standard Process (CRISP-DM) of Data Mining was introduced in order to present a industry-neutral, tool-neutral, and application-neutral data mining process (Larose, 2005). The CRISP-DM process is composed of six steps: business understanding, data understanding, data preparation, modeling, evaluation, and deployment (McCue, 2007).
1. Business Understanding – this is the initial phase which focuses on understanding the project objectives and requirements from a business perspective, then covering this knowledge into a data mining problem definition and a preliminary plan designed to achieve the objectives (Milutinovic & Patricelli, 2002). Some argue that this is the most important phase of the data mining process. This phase includes an understanding of the current practices and overall objectives of the project. During the business understanding phase of the CRISP-DM process, the analyst determines the objectives of the data mining project. Included in this phase are an identification of the resources available and any associated constraints, overall goals, and specific metrics that can be used to evaluate the success or failure of the project (McCue, 2007).
2. Data Understanding – is the phase that starts with an initial collection and proceeds with activities in order to get familiar with the data, to identify data quality problems, to discover first insights into the data or to detect interesting subsets to form hypotheses for hidden information (Milutinovic & Patricelli, 2002). The second phase of the CRISP-DM analytical process is the data understanding step. During this phase, the data are collected and the analyst begins to explore and gain familiarity with the data, including form, content, and structure. Knowledge and understanding of the numeric features and properties of the data will be important during the data preparation process and essential to the selection of appropriate statistical tools and algorithms used during the modeling phase (McCue, 2007).
3. Data Preparation – this phase covers all activities to construct the final dataset from the initial raw data. Data preparation tasks are likely to be performed multiple times and not in any prescribed order. Tasks include table, record and attribute selection as well as transformation and cleaning of data for modeling tools (Milutinovic & Patricelli, 2002). After the data have been examined and characterized in a preliminary fashion during the data understanding stage, the data are then prepared for subsequent mining and analysis. This data preparation includes any cleaning and recoding as well as the selection of any necessary merging or aggregating of data sets or elements is done (McCue, 2007).
4. Modeling – in the fourth step, various modeling techniques are selected and applied and their parameters are calibrated to optimal values. Typically, there are several techniques for the same data mining problem type. Some techniques have specific requirements on the form of data (Milutinovic & Patricelli, 2002). During the modeling phase of the project, specific modeling algorithms are selected and run on the data. Selection of the specific algorithms employed in the data mining process is based on the nature of the question and outputs desired (McCue, 2007).
5. Evaluation – at this stage in the project, the analyst have built a mode that appear to have high quality from a data analysis perspective. Before proceeding to final deployment of the model, it is important to more thoroughly evaluate the model and review the steps executed to construct the model to be certain it properly achieves the business objectives. A key objective is to determine if there is some important business issue that has not been sufficiently considered. At the end of this phase, a decision on the use of the data mining results should be reached (Milutinovic & Patricelli, 2002).
6. Deployment – the deployment phase includes the dissemination of the information. The form of the information can include tables and reports as well as the creation of rule sets or scoring algorithms that can be applied directly to other data (McCue, 2007).
Application of Data Mining by Different Companies
The benefits of using data mining are being explored by many organizations today. Successful companies are using data mining to accomplish different objectives. While the first movers come from high technology industries, companies from different industries are quickly catching up. Data mining applications reach across industries and business functions. Data mining has many varied fields of application, some of which are discussed below:
· Retail/Marketing – an example of pattern discovery in retail sales is to identify seemingly unrelated products that are often purchased together. Market basket analysis is an algorithm that examines a long list of transactions in order to determine which items are most frequently purchased together. The results can be useful to any company that sells products, whether in a sort, by catalog, or directly to the customer (Fernandez, 2003).
· Banking – a credit card company can leverage its customer transaction database to identify customers most likely to be interested in a new credit product. Using a small test mailing, the characteristics of customers with an affinity for the product can be identified. Data mining tools can also be used to detect patterns of fraudulent credit card use, including detecting fraudulent credit card transactions and identifying anomalous data that could represent data entry keying errors. It identifies loyal customers, predicts customers likely to change their credit card affiliation, determines credit card spending by customer groups, uncovers hidden correlations among various financial indicators, and identifies stock trading trends from historical market data (Fernandez, 2003).
· Healthcare Insurance – through claims analysis, data mining can predict which customers will buy new policies, defines behavior patterns of risky customers and identifies fraudulent behavior (Fernandez, 2003).
· Transportation – departments of transportation can develop performance and network optimization models to predict the life-cycle costs of road pavement (Fernandez, 2003).
· Product Manufacturing Companies – manufacturers can apply data mining to improve their sales process to retailers. Data from consumer panels, shipments, and competitor activity can be applied to understand the reasons for brand and store switching. Through this analysis, a manufacturer can select promotional strategies that best reach their target customer segments. Data mining can determine distribution schedules among outlets ands analyze loading patterns (Fernandez, 2003).
· Healthcare and Pharmaceutical Industries – a pharmaceutical company can analyze its recent sales records to improve targeting of high-value physicians and determine which marketing activities will have the greatest impact in the next few months. The ongoing, dynamic analysis of the data warehouse allows the best practices from throughout the organization to be applied in specific sales situations (Fernandez, 2003).
· Internal Revenue Service – the IRS uses data mining to track federal income tax frauds (Fernandez, 2003).
Perhaps the greatest contribution of data mining to organizations is it enables organizations to gain deeper understanding of and gather more accurate information about customers. For example, data mining is used by marketing and sales firm to analyze sales data which will allow the organizations to better predict future consumer trends. Customer transactions can also be analyzed more effectively using data mining thereby enabling companies to discover hidden, unidentified, or underlying patterns, trends and interrelationships. Such an analysis becomes more effective with the support of a data warehouse that contains internal data about current and potential customers coupled with external data about competitors and market-related activities. The outcomes of market and customer data analysis are expected to help marketing managers understand and predict future customer, product, or process behavior (Rosen, 1996 cited in Chooporian et al. 2001). In a sense, the mined data help marketing managers to understand what is likely to drive a particular customer behavior, product activity or event, and consequently, enable organizations to be proactive rather than reactive to the changing conditions in the business environment (Chooporian et al, 2001).
Data mining continues to be a useful technique for organizations and even government agencies. The author chose data mining as a topic because of its significance in knowledge management. Data mining is popular among organizations because it is applicable to almost any industry and its benefits are numerous. Data mining tools and techniques are also readily available and the data mining process has become more sophisticated over time.
Potential Problems and Pitfalls
1. Large Volume of Data
Data mining is specifically used for storing and retrieving massive amount of data. However, storing a large amount of data which cannot be handled by the organization’s hardware and software may endanger the data mining process. It is dangerous when the organization store too much information as the data mining process may become too slow and unresponsive.
2. Poor Organization of Data
When the data mining process is allowed to operate freely without clear goals, results will become unusable. There is a danger in poorly organized data as it may affect the data mining process.
3. Incongruent Data Mining Systems and Software
Successful data mining needs a variety of capabilities, calling for the employment of different systems and tools. Problems can arise when these tools are not compatible with each other, causing high overhead costs.
Chopporian, J.A. et al. (2001). “Mind your business by mining your data” SAM Advanced Management Journal, vo. 66, no. 2, pp. 45+.
Fernandez, G. (2003). Data mining using SAS applications. CRC Press.
Keating, B. (2008). “Data Mining: What is it and how is it used?”. The Journal of Business Forecasting, vol. 27, no. 3, pp. 33+.
Larose, D.T. (2005). Discovering knowledge in data: An introduction to data mining. John Wiley and Sons.
McCue, C. (2007). Data mining and predictive analysis: Intelligence gathering and crime analysis. Butterworth-Heinemann.
Milutinovic, V. & Patricelli, F. (2002). E-business and e-challenges. IOS Press.
Thierauf, R.J. (2001). Effective business intelligence systems. Westport CT: Quorum Books.