Idea to capture knowledge from different sources can be very beneficial to Business Intelligence (BI). Organizations need to collect data sources from type of structured and unstructured, including individuals' tacit knowledge in order to have the better output in data analysis. Therefore, the complexity of BI processes need to be explored in order to ensure the process will properly treat the tacit knowledge as a part of the data source in BI framework. Moreover, the linkage between unstructured data and tacit knowledge is generally consistent, for the reason that one of tacit knowledge characteristic is unstructured, which is difficult to capture, codify, estimate, investigate, formalize, write down, and communicate accurately. Cognitive approach is ideally suited for the capturing tacit knowledge as from among the massive data available these days. Typically, the organization must integrate multiple streams of data from several sources or other collaboration resources with the knowledge systems for making the decisions. This paper explores the possibility of tacit knowledge used in BI framework to perform data analysis for decision makers.
Introduction
Raw data or information retains within the organization in the form of explicit, implicit and tacit knowledge with limited resources. Several researches have been conducted in Business Intelligence (BI) and Knowledge Management (KM) domain to solve the problem by using tacit knowledge for data analysis. Yet, the new information, knowledge, and un-structured data are used to improve the decision making. The raw data and information need to be processed to acquire knowledge through the use of the analytical approach, which is normally the analyst will use the descriptive or predictive analysis approach to produce results for making a decision.
The idea of taking knowledge from different sources can be very beneficial to BI, especially for tacit knowledge. The identifying content or “data” from authors or experts in the form of tacit and “know-how” knowledge is important to be used for data analysis. Currently, the use of BI applications for managing and analyzing the explicit knowledge is the major portion of the enterprise software of BI for data analytics. Therefore, the requirement of BI application that can support for managing the tacit knowledge is crucially important. This paper will start with a discussion on how the tacit knowledge can be part of unstructured data and later can be used for data analysis in BI framework. Even though several models and frameworks have been proposed by many researchers, but the limited framework for BI system still needs to be explored. Additionally, the traditional method of BI framework can be enhanced by using the cognitive approach to handle the capturing of tacit knowledge sources.
Tacit knowledge needs to be converted to either structured or unstructured data to being codified in the BI system. The proposed model for managing tacit knowledge is developed by using KID model and cognitive approach to capture and extract tacit knowledge, and develop a new data centric model that works with traditional structured data as well as unstructured data including video, image, and digital signal processing.
METHODOLOGY
This research will adapt the hybrid methodology of qualitative and quantitative approach due to handling experiment with the human knowledge. This research has investigated the limitations of BI framework in capturing various data types to identify the problem in handling the tacit knowledge for data analysis. This has built the gap in this research and worth it to explore the solution for this problem. Several studies have been conducted in the field of BI and KM, but lacking of research work which has explored the solution for tackling tacit knowledge of data analysis in the BI system. Therefore, we argue must be a study to propose a method to handle the tacit knowledge and later can be used for data analysis in BI framework. The traditional method of BI framework will be enhanced by using the cognitive approach to handle the tacit knowledge of BI framework for data analysis.
Cognitive Approach
Cognitive Analytics
Cognitive Mapping
PROPOSED BI FRAMEWORK
The key of BI is to capture, analyze, and share such knowledge. The process of capturing knowledge with the cognitive approach might be useful in order to improve the predictive and prescriptive results BI framework. Authors show the generated KID generated model that consists of three elements, which are: D, I, and K, and also Knowledge repository, named K-store as shown in Figure 4 and Figure 5. The capital D refers to data which represent the observable properties of objects in the external world. The capital I represent the information, as the result of data which being interpreted by existing knowledge which is referred to what human have said.
The capital K refers to knowledge which is formed by assimilating the information into existing knowledge or derived from updating knowledge. D, I, and K are interrelated. Their interrelationships are defined by the three transformation functions. The KID model is a cognitive model, since data are is a cognitive process from data to knowledge. It adopts the results of psycologists' investigations, simulates human information processing and built based on our argument that any cognitive model can be built
with three transormation process from data to knowledge. The implication for the relations of data, information, knowledge and wisdom still lacks explicit and pragmatic approaches. Yet, tacit knowledge contains wisdom, where wisdom is solely owned by humans. From the model as shown as Figure 4 above, authors stated that knowledge as the basic unit of wisdom, where wisdom is also probabilistic. The cognitive approach is suitable for the "more than one" hypotheses to be analyzed. Moreover, as it is a kind of decision support that allows people to explain new opportunities, which has an impact in a positive manner. The key to BI is to capture, analyze, and share such knowledge. Thus, the process of capturing knowledge with the cognitive approach might be useful in order to improve the predictive and prescriptive results in BI applications.
