An Overview of Business Intelligence (Essay Sample)

An Overview of Business Intelligence/Data Mining
Student’s name:
Institutional affiliation:
Introduction
Business intelligence entails asset of a number of techniques, methods and tools that are used in gathering the right data and subsequently turning it into competitive knowledge and wisdom. The KDD, knowledge discovery databases is defined as the nontrivial process of making and identifying valid, potentially useful and understandable patterns of data. Data mining is another crucial element that involved various steps in the process of discovering knowledge in databases, which inputs the predominantly cleaned, search data using algorithms, transformed data and ultimately outputs the patterns as well as relationships to an evaluation step of the entire process of discovering knowledge in the databases process. As a new discipline at the interface of database technology, statistics, machine learning, and patter recognition among others, Data mining has been primarily concerned with secondary analysis of huge databases (Sabherwal & Becerra-Fernandez 2009). It generally offers a process of exploration and analysis through either automatic or semi-automatic means, where large quantities of data are easily discovered by meaning patterns and rules.
Brief Descriptions
Business intelligence and data mining are essential elements in the information technology world as they have enormous impact on businesses and organization diverse ways. Business intelligence involves various software applications that are primarily used to analyze raw data. BI associates with several activities that include data mining, querying, online analytical processing and reporting. Different companies can use BI to conveniently improve decision making, identify new business opportunities and equally cut costs (Sabherwal & Becerra-Fernandez 2009). The Business Intelligence tools that exist in the contemporary world can be easily incorporated into information systems and subsequently start analyzing the data by themselves, instead of waiting for the information technology systems to run complex.
Data mining can be well understood by establishing the various the types of its methods as well as marketing. Data mining methods are divided in multiple ways, although there are only two types commonly associated with it, especially when dealing with marketing and business intelligence. These two crucial methods include the supervised learning and unsupervised (Shmueli et al, 2011). The supervised learning, data mining method is usually associated with scientific research and commonly involves tasks where data miner subsequently needs to predict or describe the relationship that exists between sets of independent variables and the dependent variables.
Origin and Evolution
Business intelligence traces their roots to the early business applications, which supported their respective functions and became less reliable such there were no other systems that could access them. During this time, different sets of information proliferated as more departments were automated. The mergers and acquisitions also compounded the issue as companies integrated completely different systems, most of which could perform similar tasks or jobs. The first concept of business intelligence was achieved from the concept of online data warehouse, which used single system for repository in typically all data of an organization (Shmueli et al, 2011). More advancement in technology that led to the ETL, Offline Extract Transform and Load formed a better layout for the BI. Business intelligence was later developed, from the concept that was used in the ETL technology. The Evolution of BI reached its contemporary state after incorporating the ETL utilities to form the data mining engines and reporting tools.
Data mining takes roots from Statistics and Computer science, and it is sometimes referred to as Statistical learning. Although the term data mining started to be used in the 1990s, the concept has been in use since the early in1960s. Data mining was initiated through collecting and storing of data on tapes, disks and computers during its early periods of its use. The next evolutionary step happened in the 1980s upon the introduction of structured query language and relational databases (Shmueli et al, 2011). During the 1990s, it becomes highly useful in after the introduction of data warehousing. Since then, data mining has been undergoing a development process for several years, where different areas contributing to its current form.
Business importance
Business intelligence is a crucial tool in businesses. It is important because it is all about decision making, as it presents data in an easy and human readable way, such that decisions are made in a more informed way. BI is also needed for transaction processing systems to primarily provide adequate analytical and reporting requirement for the business people. Business intelligence and data mining are essential in online marketing in different ways. This is based on the need to provide ways of analyzing and effectively reporting all the valuable data that is embedded in all day application of a business, commonly supported by online transaction processing systems, OLPT. It is essential to acknowledge that without OLPT systems, businesses can hardly function, hence the incorporation of BI and DM provides a solution to technically all business operations. The key focus of such system is mainly to get all transactions sorted in a conclusive manner, as provided by both BI and DM (Sabherwal & Becerra-Fernandez 2009). Through Business Intelligence and Data Mining, many business organizations and entities find the best ways analyzing as well as reporting data simply by computerized systems.
Business Intelligence and Data mining are essential in making it possible for business entities to determine their visibility and acceptance in the market. In addition, the measure of growth of business is equally possible through a thorough use of both BI and DM. Business intelligence helps business organizations to be timely informed on the latest trends, as well as helps determines the performance of the business entities in the competitive market. This is achieved through provision of accurate data as provided by business intelligence, which also focuses on the general importance of the use of data mining. Data mining particularly helps the business entities in analytical data intelligence services by gathering information in both timely and valuable manner (Shmueli et al, 2011). Businesses of different orientations benefit from data mining as it provides them valid information that is essential in making fast and accurate decisions, subsequently leading to maximize revenues for the business entities.
Overview of Software Technologies
There several software technologies that encompass data mining subsequently enhancing business intelligence. A good example of such technologies is the Statistical Analysis System software. SAS Enterprise Miner a perfect example of the latest technologies of the Statistical Analysis System software used in most businesses today. SAS Enterprise Miner streamlines the data mining process in order to create accurate predictive and descriptive models that are based on analysis of the huge amounts of data from an enterprise or a business entity (Shmueli et al, 2011). This platform of data mining is applicable in various industries and equally provides methodologies for different business problems such as fraud detection, customer retention and attrition, house holding, marketing segmentation, database marketing, customer satisfaction, risk analysis and portfolio analysis.
The SAS Enterprise Miner supports data mining process in the following steps: sampling the data, exploring the data, modifying the data, modeling the data and assessing the data. The various steps involve vigorous processes of analyzing the data. In the first step, data is sampled through the creation of one or more data sets. In this case, the sample should be large to contain significant information, but equally small to process. It involves the importation of data, merging and filtering, as well as statistical techniques of sampling. The second step of exploring data utilizes tools to define transformations, values recording and valuable clustering among others (Sabherwal & Becerra-Fernandez 2009). The third step of modification of data involves techniques like linear and logistic regression, neural networks and decision trees among others. The fourth step of assessing data entails evaluating both usefulness and reliability of findings from the data mining process.
The table of SAS enterprise miner can be presented as follows:
NameSAS Enterprise MinerSourceSAS Miner Enter...