Business intelligent: A combination of use data mining tools in business process

Chia sẻ: Minh Minh | Ngày: | Loại File: PDF | Số trang:9

Thêm vào BST

Báo xấu

19
lượt xem 2
download

Download Vui lòng tải xuống để xem tài liệu đầy đủ

In this paper we would like to describe in detail just what Business Intelligence is and make clear the difference between Business Intelligence and Decision Support System by examining their definitions and their components. Moreover, the study case is also represented as an introduction to show how it is used in Enterprise applications.

Chủ đề:

Bình luận(0) Đăng nhập để gửi bình luận!

Lưu

Nội dung Text: Business intelligent: A combination of use data mining tools in business process

JOURNAL OF SCIENCE OF HNUE FIT., 2013, Vol. 58, pp. 79-87 This paper is available online at http://stdb.hnue.edu.vn BUSINESS INTELLIGENT: A COMBINATION OF USE DATA MINING TOOLS IN BUSINESS PROCESS Nguyen Thi Thu Thuy∗ and Hoang Quoc Minh Economic Information System Faculty, Vietnam University of Commerce ∗ E-mail: nguyentthuthuy@gmail.com Abstract. Business Intelligence is something which is used in many business oriented applications. What is different between Decision Support Systems and Business Intelligence? In this paper we would like to describe in detail just what Business Intelligence is and make clear the difference between Business Intelligence and Decision Support System by examining their definitions and their components. Moreover, the study case is also represented as an introduction to show how it is used in Enterprise applications. The BI is used for Cau Giay District People’s Committee Information System as OLAP cube in many dimension to serve many users making business decisions. Keywords: Business Intelligence (BI), Decision Support System (DSS), Data Mining, Business Decision. 1. Introduction Data Mining is a powerful tool that is used in business, bioinformatics, healthcare, etc. It is used, for the most part, to generate alternative models for decision making. Even though data mining has been successfully used in the formulation of various business processes as well as to transfer innovations from academic research into the business world, the gap between the problems that the research community works on and real-world problems is significant. With Business Intelligence (BI), data mining tools are used in the process of making business decisions. In 1989, Howard Dresner [10] used the term “Business Intelligence” to describe systems that help decision makers understand the state of their company’s world. Since then, there has been a steady growth in the use of both BI solutions and their adoption and usage. While large organizations were quick to embrace BI, with the availability of online SAAS solutions and Cloud, small and medium size businesses have also embraced business intelligence as a key differentiator [10]. Demand for Business Intelligence (BI) applications continues to grow even at a time when demand for most information technology (IT) products is soft [8], [9]. Business 79
Nguyen Thi Thu Thuy, Hoang Quoc Minh Intelligence systems combine operational data with analytical tools, such as Data Mining tools, to present complex and competitive information to planners and decision makers. Business Intelligence is used to understand the capabilities available in the firm; the state of the art, trends, and future directions in the markets, the technologies and the regulatory environment in which the firm competes; and the actions of competitors and the implications of these actions. The emergence of the data warehouse as a repository, advances in data cleansing, increased capabilities of hardware and software and the emergence of the web architecture all combine to create a richer business intelligence environment than was available previously. Although business intelligence systems are widely used in industry, research in these systems is limited. An explanation of the nature of BI and applications in possible use of BI by the Cau Giay District People’s Committee is also proposed. 2. Content 2.1. Business Intelligence 2.1.1. What is Business Intelligence? Business intelligence is a relatively new term in information technology and the meaning of business intelligence differs from context to context. The term was first used by Gartner and popularized by analyst Howard Dresner [10]. It describes the process of turning data into information and then into knowledge. The claim is that such intelligence is more useful to the user as it passes through each step. BI describes a set of concepts and methods to improve business decision making by using fact based support systems. Gartners’s definition of business intelligence includes all the ways in which an enterprise can explore, access and analyze information in the data warehouse to develop insights that lead to improved, informed decisions. According to whatis.com “Business Intelligence (BI) is a broad category of applications and technologies for gathering, storing, analyzing, and providing access to data to help Enterprise users make better business decisions”. “Business intelligence (BI) is also defined as the ability of an organization to take all its capabilities and convert them into knowledge. This produces large amounts of information which can lead to the development of new opportunities for the organization. When these opportunities are identified and a strategy has been effectively implemented, they can provide an organization with a competitive advantage in the market and stability in the long run (within its industry)” [1], [7]. It can be seen that BI is defined as a decision support system (DSS). However, many Vietnamese people do not understand that BI is another name for DSS when used in business. So, what is difference between the two? Let go back to the definition of DSS: According to Whatis.com: “A decision support system (DSS) is a computer program 80
Business intelligent: a combination of use data mining tools in business process application that analyzes business data and presents it so that users can make business decisions more easily.” Also: “A decision support system (DSS) is a computer-based information system that supports business or organizational decision-making activities.” (Wikipedia). According to [6], DSS dates back to the late 1960s and was used in theory developments in the 1970s and, in the early and mid 1980s, it was used in the implementation of financial planning systems, spreadsheet-based DSS and Group DSS. Data warehouses, Executive Information Systems, OLAP and Business Intelligence all evolved in the late 1980s and early 1990s. The field of computerized decision support is expanding to use new technologies and to create new applications. Therefore, BI can be seen as a part of a field in the DSS area. We can see BI is an aspect of DSS in Figure 1 below. It is clear that BI is a combination of the use Data Mining tools and Text Mining in Data Warehouse to extract knowledge needed for business decision making. Looking at it another way, we can understand that BI is a set of methodologies, processes, architectures, and technologies that transform raw data into meaningful and useful information that can be used to enable more effective strategic, tactical, and operational insights and decision-making [3]. Figure 1. Components of BI and DSS [6] 2.1.2. Business Intelligence Frame Work BI can use both structured and semi-structured data in its processes. For structure data, BI can withdraw data from a data warehouse. Normally, this data is extracted from the information system via internet browser technologies. Figure 2 will show the BI framework for both structured and semi-structure data. To create business intelligence information, the integrated data are searched for, analyzed and delivered to the decision maker. For structured data we can use tools such as Enterprise Resource Planning (ERP) systems, data-mining tools and on-line analytical processing tools (OLAP). However, at the moment, a different and less sophisticated set of analytic tools is currently required to deal with semi-structured data (such as email, web pages, reports, etc.). In this paper, the case study of BI iinvolves only structured data. 81
Nguyen Thi Thu Thuy, Hoang Quoc Minh Details about BI using semi-structured data can be seen in [4]. Figure 2. Business Intelligence Data Framework [5] The architecture for Structured Data can be seen in Figure 3. Information from alternative systems such as ERP, CRM, etc can be stored in Data Warehouse. Only BI needed data will be saved in Data Mart. Via Network Distribution, output can take several forms including exception reports, routine reports and responses to specific request. The outputs are sent whenever they need to be required on demand. Figure 3. Typical BI Architecture for Structured Data [5] 2.1.3. Business Intelligence for the Cau Giay District People’s Committee In Vietnam, many companies have deployed information systems such as ERP and CRM. In these systems most of the data is ready for analysis. Most company reports show only specific activities, such as accounting reports and executive operations, of the various offices of the company. The head of the company or the management board does not have enough information to make a decision because this information is not there in the company’s report. The lack of analysis tools which could combine data from alternative reports sources is one reason why the above issue exists. In the Cau Giay District People’s Committee’s information system, such is the case. A general and inclusive online summary report can not be provided because there are available only alternative reports from individual offices, generated by each of those offices. In this paper we would like to propose a BI framework that can be used in the 82
Business intelligent: a combination of use data mining tools in business process Cau Giay District People’s Committee’s information system and would result in a vast improvement. The Cau Giay District People’s Committee can now work with 404 administrative procedures (258 district procedures and 146 wards procedures). People in the district can download all 404 level 2 administrative forms of alternative procedures from a website. The number of administration procedures of level 3, people will find forms for only 8 procedures on the website. The software for this, installed in 2006, is SQL server 2000. The disadvantage of this system is that handles only the manual reports generated by the office. Thus, individual officers generally need to refer to additional paper documents. The result is that data will appear in an officer’s report that is not in either the database or a system report. OLAP technology can produce a report automatically for managers who go online with data taken from the system. Therefore, the reports using OLAP would be more accurate than manually derived reports. Moreover, OLAP reports would save the time by scanning data from all databases because it is built based on the OLAP database in the servers. In this paper, the BI is represented in the use of MS Visual Studio in building an OLAP cube for analysis data in a One-Door database. This database is in the Cau Giay District People’s Committee Information System. The framework for the One-Door database can be seen in Figure 4. Figure 4. BI Framework for One-Door Database The Cau Giay District People’s Committee Information System contains many databases, the largest being the One-Door database which includes 90 tables. There are an additional 68 relational tables, and others that have no relevance. The raw data (papers and excel files) is taken from the many offices in the Committee and the many Communes in the District. Committee Officers clean data subjectively and input that into the system. For example, system default values will be used to provide data that is missing in a form. To understand the use of BI in the analysis of business data we need to be clear on the definition of OLAP cube in the BI context. It can be understood as an array of data that has 0 or many dimensions where each dimension is a table that attributes to the analysis 83
Nguyen Thi Thu Thuy, Hoang Quoc Minh of business data in the search for business intelligence in online analytical processing (see Figure 6 for an example of creating alternative dimensions for a One-Door database). From this definition, it is clear that the analytical business data obtained via online processing differs greatly from the that obtained in traditional analysis using alternative known tools such as MS Excel or SPSS. The advantage here is that we can represent data in many dimension to extract the needed data for business processes. More detail about OLAP cube for BI can be seen in [2]. Figure 5. Table list and some table relationships in One-Door database Figure 6. Select dimension for One-Door Cube 84
Business intelligent: a combination of use data mining tools in business process Figure 7. Report example • Introduction to the One-Door database: This database serves the following functions: Declare and mange the list location and administrative procedures of the Cau Giay District People’s Committee offices; Receive administrative documents from citizens; Set the time to process and return documents received; Delivery of documents to the appropriate office; Update documents; Notify offices when deadlines to return documents draws near; Generate a quarterly work reports for each offices. • Database structure: This includes 90 tables to serve about 404 administration procedures (see in Figure 5). Figure 8. Cube ND_ThuTuc example • Design cube, Dimension table and Fact table: The cube is designed by using BIDS tools in MS visual Studio. See Table 1 for Fact Tables. 85
Nguyen Thi Thu Thuy, Hoang Quoc Minh The dimension for the One-Door Cube can be seen in Figure 6. The cube can be deployed to analyze service within the server. A detailed report will be built with data taken from the One-Door Cube. In Figure 7, the report shows the summary of administration procedures, grouped by professional area, that is to be delivered to other administrative levels when there are complaints from citizens. This data is taken from the alternative dimensions in the selected Fact Tables in the One-Door Cube (see Figure 8) in the server. Table 1. List of Fact Tables Table Name Table Name DM_CanBoThuTuc DM_CanBoThuTucND DM_SoNganh DM_SoNganhHinh DM_ThuTuc DM_ThuTucHoSo MC_EventsHoSo MC_NhanDuLieu MC_NhanDuLieuTra MC_TheoNhomYeuCau MC_YeuCauChuyenDi MC_YeuCauGiaoPhong ND_QuyetDinhChungNhan ND_QuyetDinhChungNhanBienDong ND_ThuTucCotThem ND_ThuTucCotThemCm ND_YeuCauHoSoGomCo ND_YeuCauLog DM_MucTaiLieuFile DM_PhuongXaHinh DM_SoNganhThuTuc DM_TaiKhoan MC_EventsAttach MC_EventsConcurrent MC_NhanDuLieuNhan MC_NhanDuLieuPhuongXa MC_TruyenDuLieu MC_YeuCauAttach MC_YeuCauTra ND_QuyetDinhAttach ND_Taikhoan ND_TheoNhomYeuCau ND_ThuTucHoSo ND_YeuCauCotThem ND_YeuCauTra 3. Conclusions and Further Works The BI definition seems to be a detailed definition of Data–driven Decision Support System (DSS) as is commonly used in Business Information Systems. When there is a clear understanding of this definition, researchers can build accurate and adaptive application models for their business organizations. This paper attempts to clarify the differences between DSS and OLAP BI. Moreover, the application of the One-Door cube 86
Business intelligent: a combination of use data mining tools in business process built for the Cau Giay District People’s Committee Information System is an example of the use of OLAP BI in the real world. We hope that Data-driven DSS or BI can be deployed in many company applications to help businesses make challenging decisions. Additional work on the Cau Giay District People’s Committee Information System will deal with semi-structure data such as administration procedures via emails from citizens or reports from alternative offices. REFERENCES [1] Cao, L.; Yu, P.S.; Zhang, C.; Zhang, H., 2009. Data Mining for Business Applications. Springer publication. [2] Carl Dubler and Colin Wilcox. "Just What Are Cubes Anyway? (A Painless Introduction to OLAP Technology)". Msdn.microsoft.com. Retrieved 2012-07-25. [3] Evelson, Boris, 2008. "Topic Overview: Business Intelligence" for Decision-Support Applications. Boston, MA: Addison-Wesley. [4] Moss, L.T. and S. Atre, 2003. Business Intelligence Roadmap: The Complete Project Lifecycle. [5] Negash, S, 2004. "Business Intelligence". Communications of the Association of Information Systems, pp 177–195. [6] Power, D.J., 2011. A Brief History of decision support system. Available at http://dssresources.com/history/dsshistory.html. [7] Rud, Olivia., 2009. Business Intelligence Success Factors: Tools for Aligning Your Business in the Global Economy. Hoboken, N.J: Wiley & Sons. [8] Soejarto, A., 2003. “Tough Times Call for Business Intelligence Services, an Indisputable Area of Growth”. Available at http://vb.channelsupersearch. com/news/var/40682.asp. [9] Whiting, R., 2003. “Look Within-Business-Intelligence Tools have a New Mission: Evaluating All Aspects of a Company’s Business”. InformationWeek. [10] website: http://thebusinessintelligenceguide.com/History_of_BI.php. [11] website: www.caugiay.hanoi.gov.vn 87