1 / 38

Chapter 9 – Business Intelligence

Chapter 9 – Business Intelligence. Announcement. Thursday Night we will begin at 5:30. Why do organizations need BI?. Why do organizations need BI?. Tons of data out there! In 2002, 2 exabytes were created In 2008, 70 exabytes 14x words spoken by human beings ever

ronli
Download Presentation

Chapter 9 – Business Intelligence

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Chapter 9 – Business Intelligence

  2. Announcement • Thursday Night we will begin at 5:30

  3. Why do organizations need BI?

  4. Why do organizations need BI? • Tons of data out there! • In 2002, 2 exabytes were created • In 2008, 70 exabytes • 14x words spoken by human beings ever • Business Intelligence – information containing patterns, relationships, and trends • How do you get it out???? BI Systems

  5. What BI Systems are available?

  6. What BI Systems are available? • BI System – Information system that employs BI tools to produce and deliver information • Type of systems depend on tools in use • Categories of tools • Reporting - Simple • read, process, format, deliver • Used to assess results – What happened? • Data mining - Sophisticated • Searching for patterns or relationships • Used to make predictions – What will happen? • Knowledge management • Used to store employee knowledge and make it available to others • Source of data – humans • How do you handle what is happening?

  7. Tools vs. Applications vs. Systems • Tool – one or more computer programs that implement the logic of a particular procedure • Example: Decision tree analysis • Application – use of a tool on a particular type of data for a particular purpose • Example: Assess risk for a loan to default • System – has all 5 components (hardware, software, data, people, procedures) delivering results of a BI application • Example: delivers results to loan officer who makes final decision

  8. Reporting Applications • Reporting application inputs data from one or more sources and applies a reporting tool to that data to produce information. This is then delivered to users by reporting system. • Operations commonly used: • Sorting • Grouping • Calculating • Filtering • Formatting

  9. Some Dashboards to see • http://dashboard.virginiadot.org/ • http://dashboard.imamuseum.org/ • http://buildingdashboard.com/clients/jmu/

  10. Analytical Tools • RFM Analysis – ranks information according to purchasing behavior – gives customers an RFM Score (1 – 5, 1 being the top 20%) • How Recently? • How Frequently? • How much Money?

  11. In Class Exercise • Review the data. • Sort the data • Split into 20% increments for R, F, and M • 1 for Most Recent, 5 for Least Recent • 1 for Most Frequent, 5 for Least Frequent • 1 for Most Money, 5 for Least Money • Assign scores to each customer

  12. What would you do with each?

  13. OLAP – Online Analytical Processing • More generic than RFM • Dynamic – viewer can change the format • Measures and Dimensions • Measures – data item of interest • Total sales, average sales, average cost, etc. • Dimension – characteristic of a measure • Purchase date, customer location, etc.

  14. Example – An OLAP Cube or report • Users can alter the format • Possible to drill down into the data • Requirements • Computing power • Tools may be costly Measure Dimension

  15. A Demo of a Tool • http://www.tableausoftware.com/products/tour

  16. Data Mining • Statistical techniques to find patterns and relationships among data and use it for classification and prediction • Data mining techniques are a blend of statistics and mathematics, and artificial intelligence and machine-learning

  17. What’s the difference between supervised and unsupervised data mining?

  18. Supervised vs. Unsupervised data mining • Unsupervised data-mining characteristics: • No model or hypothesis exists before running the analysis • Analysts apply data-mining techniques and then observe the results • Analysts create a hypothesis after analysis is completed • Cluster analysis, a common technique in this category groups entities together that have similar characteristics • Supervised data-mining characteristics: • Analysts develop a model prior to their analysis • Apply statistical techniques to estimate parameters of a model • Regression analysis is a technique in this category that measures the impact of a set of variables on another variable • Neural networks predict values and make classifications

  19. Market-Basket Analysis • Data mining tool for determining sales patterns • Helps businesses create cross-selling opportunities • Terms used with this type of analysis • Support—the probability that two items will be purchased together • Confidence—a conditional probability estimate • Lift – ratio of confidence to support • Complex, requires analytical tools

  20. Market-Basket Example: Transactions = 400

  21. Decision Trees • Hierarchical arrangement of criteria that predicts a classification or value • Unsupervised data-mining technique that selects the most useful attributes for classifying entities on some criterion • If…then rules

  22. Example • Select attributes that are most useful for classifying • Predicting Grades for Students in COB 204 • What are some attributes/characteristics we should consider? How do businesses use decision trees?

  23. College Admissions Decision TreeGroup Assignment – Ethics p.303

  24. Data Warehouses and Data Marts • Address the problems companies have with missing data values and inconsistent data • Help standardize data formats between operational data and data purchased from third-party vendors • Prepare, store, and manage data specifically for data mining and analyses.

  25. Problems with Operational data

  26. The Curse of Dimensionality • The more attributes there are, the easier it is to build a model that is worthless

  27. Data Marts vs. Data Warehouses • Data mart is smaller than a warehouse • Data mart addresses a particular component or function

  28. Knowledge Management Applications • KM – process of creating value from intellectual capital and sharing with others who need it • Data mining and reporting create new information • KM shares known information

  29. What are the benefits of KM?

  30. Benefits of KM • Fosters innovation – free flow of ideas • Improves customer service – faster response time • Boosts revenues – get product to market faster • Enhances retention – recognize/reward knowledge • Streamlines operations – eliminates/reduces redundant or unnecessary operations • Preserves organizational memory

  31. Sharing Document Content • Indexing • Need to be able to easily access information • Need keyword searchability • Need quick response • RSS – Real simple syndication • Think of it as an email system for content • Subscribe to magazines, blogs, websites, and other sources – RSS Feeds

  32. Example

  33. Expert Systems • Rule based systems using if…then logic • Created by interviewing experts and codifying their decisioning (vs. decision trees that review past data and performance) • Can have hundreds of thousands of rules (vs. <12 in decision trees)

  34. Expert System Problems • Difficult and expensive to manage • Difficult to maintain • Implications of rule changes • Difficult to perform at same level as real experts • Example - medicine

  35. How are BI applications delivered?

  36. Delivery of Business Intelligence Applications

  37. Mgt Functions of BI Servers • Maintains metadata about the authorized allocation of BI results to users • Tracks what results are available, who is authorized to view them, and when the results are provided to users • Options for managing results • Users can pull their results from a Web site using a portal server with a customizable user interface • A server can automatically push information to users through alerts which are messages announcing events as they occur • Portal servers – allow for customization of the interface • A report server, a special server dedicated to reports, can supply users with information.

  38. Delivery Functions • Characteristics of the delivery function of a BI server: • Tracks authorized users. • Tracks the schedule for providing results to users. • Uses exception alerts that notify users of an exceptional event. • Procedures used depends on the nature of the BI system. • Procedures tend to be more flexible than those in an operational system because users of a BI system tend to be engaged in work that is neither structured nor routine. • Procedures are determined by unique requirements of users.

More Related