Business Analytics Frameworks PDF

IT2111 BUSINESS ANALYTICS FRAMEWORKS - The collected data is stored in data warehouse and then...

IT2111 BUSINESS ANALYTICS FRAMEWORKS - The collected data is stored in data warehouse and then analyzed for decision making. Various tools used in data layer Framework for Business Analytics include: A general framework for Business Analytics (BA) consists of four o Data Warehouse layers: Data layer, Analytics layer, Reporting/Visualization layer, - Oracle Corporation defines a data warehouse as a and Access layers as presented in Figure 1. collection of corporate information derived directly from operational systems (internal sources) and some external data sources. - Data warehouse is a copy of transaction data specifically structured for query and analysis. It is informational, analysis and decision support oriented, not operational or transaction processing oriented. - Data in a data warehouse is integrated, subject-oriented, non-volatile, and time-variant. o Extract, Transform and Load (ETL) - Before a data warehouse is populated with data from internal sources as well as external sources, data needs to be transformed. This transformation is called extract, transform and load (ETL) and performs the following functions: ▪ Extract – Data is extracted from many sources including internal or external sources. It is then consolidated, and non-relevant data is filtered out. ▪ Transform - Extracted data is validated and cleaned up to correct missing, inconsistent, or invalid values. Data is integrated into a standard format and business rules are applied that map data to the warehouse schema. Figure 1. Framework for Business Analytics ▪ Load - Cleansed data is then loaded into the data warehouse/ data mart. 1. DATA LAYER - Data is present in many places in many forms, so it needs to o Data Mart be gathered in one place. Data is collected from internal as - Also known as localized data warehouses, are small- well as external sources. sized data warehouses, typically created by individual - Internal sources of data include the operational database of divisions or departments to provide their own decision an organization where daily transactions are stored while support activities. external sources of data include suppliers, customers, competitors, government agencies, Internet, etc. 02 Handout 1 *Property of STI  [email protected] Page 1 of 3  IT2111 2. ANALYTICS LAYER - In this layer, data from Data Warehouse/Data Mart are b. Balance Scorecards analyzed by using descriptive, predictive, or prescriptive o Balanced scorecards are semi-standard structured analytics. reports, supported by design tools and techniques, that - Various techniques that are used in this layer are: can be used by managers to keep track of the execution of activities by the staff within their control and to monitor a. Data Mining the consequences arising from these actions. o The process of exploration and analysis, by semi- o They are performance metrics to identify and improve automatic or automatic means, of huge quantities of various internal functions and their resulting external data in order to discover meaningful patterns and outcomes. BSC enables organizations to put the strategy rules into practice by measuring and delivering feedback to the o The technique that includes management science, organizations. statistical, mathematical and financial models and methods, used to find the vital relationships between c. Reports: These are the written documents relating to the variables in the historical data, perform analysis on situation and can be created by the end users by supplying the data or to forecast from data. parameter data. The pre-executed report results are cached in order to support interactive and high-performance viewing b. Multidimensional Data Analysis of these reports. o Also known as Online Analytical Processing (OLAP), it is part of the wider variety of business intelligence d. Ad hoc Reports: Contrary to standard reports which are software that enables managers, executives, and predefined and routinely processed, ad hoc reports are analysts to gain insight into data through rapid, generated when the need arises. They enable users to reliable, collaborative access to a wide range of produce their own customized reports without relying on the multidimensional views of information. IT team. o It also allows business analysts to rotate data, changing the relationships to get more detailed e. Alert: A type of report that is automatically triggered when an insight into corporate information. event occurs, e.g. an e-mail or SMS message is sent to the customer when the product becomes available which he had 3. REPORTING/VISUALIZATION LAYER previously tried to purchase, or an alert can instantly notify the - There are various tools used in this layer. manager if the sales numbers fall below the acceptable level. a. Dashboards o Dashboards are the tools for visualization of important Types of Analytics business data presented in the form of graphic indicators, charts, and tables. There are four types of advanced analytics namely: Descriptive, o A digital dashboard provides the user a graphical high- diagnostic, predictive, and prescriptive. level view of business processes that can be drilled down to find more details on a particular business process. 1. Descriptive /Reporting Analytics o It organizes and reflects the information into the user - Descriptive analytics gives information about the past interface in an easy, interactive, and intuitive manner. performance or state of a business and its environment by 02 Handout 1 *Property of STI  [email protected] Page 2 of 3  IT2111 using data that is stored in databases/data warehouses. It Rough Set are used for customer identification which helps companies to gain insight from historical data with includes target customer analysis and subsequently reporting, scorecards, clustering. classifying the segments of potential customers so that - Descriptive analytics provides routine, regular and Ad hoc organizations can direct their resources and efforts into reports that helps companies to look at the facts like, what has attracting the target customer segments. happened, where, and how often. - Visualization has become an important component of b. Clustering: Clustering techniques can be used to divide descriptive analysis as it can develop powerful insights into customers into different groups in order to target specific the actions and operations of a company. promotional campaigns to them. 2. Diagnostic Analytics - It focuses on past performance to determine the answer to the c. Association: It can identify the relationships between questions like why it is happening or why something different purchasing behaviors, i.e., if a buyer buys one happened. product, it can predict the other items that he/she is likely - It gives companies deep insight into a problem by techniques to purchase, thus helping in the promotion of related such as drill-down, data discovery, data mining, etc. to find out products. dependencies and to discover patterns from the historical data. 4. Prescriptive/Optimization Analytics - The outcome of this analysis is mostly an analytic dashboard. - It helps to choose the best possible outcome by evaluating a number of possible outcomes. 3. Predictive Analytics - Enterprise level optimization models join the descriptive and - Predictive analytics tools determine the probable future predictive models together with probabilistic and random outcome for an event, or the likelihood of the situation methods such as Bayesian models or Monte Carlo Simulation occurring and identify relationship patterns. Its objective is to to assist in the determination of the best course of action understand the causes and relationships in the data to make based on various “what if” scenario assessments. accurate predictions. - It is an application of statistical, data mining, or visualization techniques to detect patterns and anomalies in detailed REFERENCES: transactions. Analysts use patterns into models that can be applied to new transactions to predict behavior or outcomes. Ahmad, Rafi. (2019). Business analytics: A framework. - For example, it can predict mixed analysis like, the customers Retrieved from that are most likely to shift to a competitor, find the customers https://www.researchgate.net/publication/332569572_Busine that are credit risk, what a buyer is likely to buy and in what ss_Analytics_A_Framework. quantity, what promotional campaign customers are likely to Camm, J.D., Cochran, J.J., Fry, M.J., Ohlmann, J.W., respond. Anderson, D.R., Sweeney, D.J., & Williams, T.A. (2018). - Various techniques of predictive analytics include: Essentials of business analytics (3rd ed.). Cengage Learning. a. Classification: classification techniques like Logistic Evans, J. (2017). Business analytics: Methods, models, and Regression (LOG), K-Nearest Neighbors, Artificial Neural decision (2nd ed.). Pearson Education Limited. Networks (ANN), Decision Trees, Support Vector Machines, Fuzzy Sets, Genetic Algorithms (GAs), and 02 Handout 1 *Property of STI  [email protected] Page 3 of 3