Business Intelligence functionality | My Assignment Tutor -

Business Intelligence1Pearson BTEC HND in Computing(RQF)Unit 14: Business Intelligence (L5)Week 4LO2Learning Outcome 2: Compare the tools and technologies associatedwith business intelligence functionality.AgendaBusiness Intelligence functionality• Analysing data, decision-making, problem solving anddesigning more intuitive/innovative systems.Decision Support Systems• History and development of decision support systems• Introduction to data mining, data integration, dataquality and data warehousing.Student activity and discussion: Students to findexamples of transaction processing systems,management information systems, decision supportsystems and expert systems.Business Intelligence23Decision Making Dimensions and BI4Order Fulfillment Decisions and BIBusiness Intelligence35Shopping Decisions and BI6Procurement Decisions and BIBusiness Intelligence47Data Mining• Objective: Fit data to a model• Potential Result: Higher-level meta information thatmay not be obvious when looking at raw data• Similar terms• Exploratory data analysis• Data driven discovery• Deductive learning8Examples• Database• Data Mining– Find all customers who have purchased milk– Find all items which are frequently purchasedwith milk. (association rules)– Find all credit applicants with last name of Smith.– Identify customers who have purchased morethan $10,000 in the last month.– Find all credit applicants who are poor creditrisks. (classification)– Identify customers with similar buying habits.(Clustering)Business Intelligence59Data Mining Models and Tasks10Basic Data Mining Tasks• Classification maps data into predefined groups orclasses• Regression is used to map a data item to a realvalued prediction variable.• Clustering groups similar data together intoclusters.• Summarization maps data into subsets withassociated simple descriptions.• Link Analysis uncovers relationships among data.Business Intelligence611Example: Time Series Analysis• Example: Stock Market• Predict future values• Determine similar patterns over time• Classify behavior12Data Mining vs. KDD• Knowledge Discovery in Databases (KDD): processof finding useful information and patterns in data.• Data Mining: Use of algorithms to extract theinformation and patterns derived by the KDDprocess.Business Intelligence713Social Implications of DM• Privacy• Unauthorized useData Quality© Cranfield University 2013 14Business Intelligence8Examples of Poor Data QualityExamples of Poor Data QualityBusiness Intelligence9Examples of Poor Data QualityExamples of Poor Data QualityBusiness Intelligence10Poor Data Quality: waste of timeThe equivalent of 2700cashiers per year spendtime trying to solvethese problemsPoor Data Quality Leads to …• Delays• Wrong product delivery• Wrong place delivery• Wrong Package Size• Damage to the product• Waste of material• …Business Intelligence11Data Management ComplexityData Management ComplexityBusiness Intelligence12Sources of Poor Data Quality1. Entry quality: Did the information enter the system correctly at the origin?2. Process quality: Was the integrity of the information maintained during processingthrough the system?3. Identification quality: Are two similar objects identified correctly to be the same ordifferent?4. Integration quality: Is all the known information about an object integrated to thepoint of providing an accurate representation of the object?5. Usage quality: Is the information used and interpreted correctly at the point ofaccess?6. Aging quality: Has enough time passed that the validity of the information can nolonger be trusted?7. Organisational quality: Can the same information be reconciled between twosystems based on the way the organisation constructs and views the data?23B2B Data Management© Cranfield University 2013 24Business Intelligence13B2B2C Data Management25 Complete & accurate logisticsdata for efficient & integratedoperationDeliver rightfirst timeDeliver topromise atlowest cost RetailerLogisticsprovider Qualityinformationbuilds brandExperiencebuilds loyaltyHarmonised data makesshopping simple & convenientSALES COST Data Quality Dimensions© Cranfield University 2013 26 CompleteThe extent to which the information is comprehensive for the planning tasksThe information includes all necessary valuesThe information includes all necessary explanations of the valuesConciseThe extent to which the information can be used directly, without a need of reworking before use, in termsof format, content, and/or structureThe information can be used directly, without reworkingReliableThe extent to which the information provided to the planning staff is accurateThe information is correct, i.e. reflecting the true demandThe forecast error is low and reflects true demandTimelyThe extent to which the information is delivered in time and at correct intervals, i.e. not too often or tooinfrequently for the planning processThe information is received in time for the planning taskValidThe extent to which the information measures what it should measureThe customer uses the same measures as you areThe customer uses the same definitions as you areAccessibleTo which extent the planning information is easy to access when requiredThe information is easy to access at the customer when requiredThe information is easily obtainable internally when it needs to be recreatedCredibleThe extent to which planning information is accepted or regarded as true, real, and believableThe received information is believableRelevantThe extent to which the planning information is appropriate for the tasks and applicationsThe received information is relevant for the task/applicationUnderstandableThe extent to which information is easy to use but also easy to learn and easy to manipulate, aggregate, andcombine with other informationThe information is easy to understandThe information is easy to rework to fit our needs Business Intelligence14Data Quality – Hospital© Cranfield University 2013 27