Data Mining: Its Application in Knowledge Management
Knowledge within the contemporary information era is becoming an important organizational resource that provides a competitive advantage, giving rise to initiatives for knowledge management (KM). Several organizations have a vast amount of data in their store but are unable to discover valuable information hidden in it by transforming the data into valuable and useful knowledge. Management of knowledge resources faces a great challenge because various organizations employ information technology (IT) in it to support the creation, division, incorporation, and distribution of knowledge (Silwattananusarn & Tuamsuk, 2012). However, data mining is the practice of utilizing tools to get viable knowledge from large datasets. According to Silwattananusarn and Tuamsuk (2012), data mining in KM is helpful in two ways;
- Distribution of ordinary knowledge of the industry aptitude context amongst the miners of data.
- Use of data mining as a means of extending human know-how.
This paper seeks to survey the mining of data application in KM through a review of the literature between 2007 and 2012 (Silwattananusarn & Tuamsuk, 2012).
According to Silwattananusarn and Tuamsuk (2012), there are several procedures in data invention in databases process, which involve;
- Selection: Selecting data that is pertinent to the analysis from the database.
- Preprocessing: Removing noise as well as inconsistent data and combining multiple data sources.
- Transformation: Changing data to the appropriate forms and performing data mining.
- Data Mining: Choose an algorithm to mine data appropriate to patterns in the data and extract data patterns.
- Evaluation: Interprets these patterns into information by eliminating superfluous and immaterial ones and deducing the constructive patterns into terms understandable by the human.
Further Silwattananusarn and Tuamsuk (2012) states that the main six functions of data mining are;
- Classification: This entails finding models that classify and analyze data items into various predefined classes.
- Regression: Entails mapping item of data to real-valued forecast variable (Silwattananusarn & Tuamsuk, 2012).
- Clustering: Entails recognizing a restricted set of huddles to illustrate the data.
- Dependency Modeling: Entails finding a model that explains important infatuation amid variables (Silwattananusarn & Tuamsuk, 2012).
- Deviation Detection: Involves determining the most vital modification in the data.
- Summary: Entails discovering a solid explanation for a division of data.
This is an attempt to improve helpful information in a group (Silwattananusarn & Tuamsuk, 2012). To achieve this, the senior management should encourage communication, offer learning opportunities, promotion, and sharing of proper knowledge artifacts. This process focuses on the knowledge flow and process of creating, sharing, and distributing knowledge (Silwattananusarn & Tuamsuk, 2012). Information technology (IT) is useful in facilitating each of the knowledge units of capture, sharing, creation, acquisition, dissemination, and application.
Application of Data Mining in Knowledge Management
Data mining is applicable to knowledge management for effectively capturing, storage, retrieval, and knowledge transfer. Various reviewed articles discussed more;
This is divided into eight groups in an attempt to store and manipulate knowledge and data mining aids that include; healthcare organization, retailing, finance/banking, small and middle business, entrepreneurial science, business, collaboration and teamwork, and the construction industry (Silwattananusarn & Tuamsuk, 2012).
There are eight types of organizational domains for data mining collaboration in the creation of knowledge that include; healthcare system domain, construction industry domain, retailing domain, financial domain, small and middle business domain, research assets domain, business domain and collaboration and teamwork domain (Silwattananusarn & Tuamsuk, 2012).
Knowledge management is a very vital organizational resource because it is highly demanded in development. Useful knowledge has a significant approach for management and decision-making. Data mining as part of KM helps various researchers apply it in KM technologies domains. Techniques for data mining have a major impact on the KM practice and present an important challenge for future research on knowledge and information systems.
Silwattananusarn, T., & Tuamsuk, K. (2012). Data Mining and Its Applications for Knowledge Management: A Literature Review from 2007 to 2012. International Journal of Data Mining & Knowledge Management Process, 2 (5).