Oracle Advanced Analytics For Fraud And Anomaly Detection
Oracle Advanced Analyticsfor Fraud and Anomaly DetectionMake Big Data Analytics SimpleCharlie Berger, MS Engineering, MBASr. Director Product Management, Data Mining and Advanced Analyticscharlie.berger@oracle.com www.twitter.com/CharlieDataMineCopyright 2015 Oracle and/or its affiliates. All rights reserved. Oracle Confidential – Internal/Restricted/Highly Restricted
Safe Harbor StatementThe following is intended to outline our general product direction. It is intended forinformation purposes only, and may not be incorporated into any contract. It is not acommitment to deliver any material, code, or functionality, and should not be relied uponin making purchasing decisions. The development, release, and timing of any features orfunctionality described for Oracle’s products remains at the sole discretion of Oracle.Copyright 2015 Oracle and/or its affiliates. All rights reserved. 2
Fraud StatisticsBy The Numbers Overall– Conservatively, fraud steals 80 billion a year across all lines of insurance.(Coalition Against Insurance Fraud est.).– Fraud comprises about 10 percent of property-casualty insurance losses and loss adjustment expenseseach year. Fraud costs for insurers– Fraud accounts for 5-10 percent of claims costs for U.S. and Canadian insurers. Nearly one-third ofinsurers (32 percent) say fraud was as high as 20 percent of claims costs;– About 35 percent say fraud costs their companies 5-10 percent of claim volume. More than 30 percentsay fraud losses cost 10-20 percent of claim volume;– Detecting fraud before claims are paid, and upgrading analytics, were mentioned most often as theinsurers’ main fraud-fighting s.htm#.VfreKRFVhBcCopyright 2015 Oracle and/or its affiliates. All rights reserved. 3
Fraud StatisticsBy The Numbers Medicare & Medicaid– Nearly 80 billion of improper Medicare and Medicaid payments were made in FY 2014;– Anti-fraud efforts recovered 3.3 billion in taxpayer dollars in FY 2014; and– 7.70 was returned for every anti-fraud dollar invested. This is about 2 higher than the average ROI since1997. It’s also the third-highest ROI. (U.S. Department of HHS, March 2015) Automobile - Bodily injury claims– Staged-crash rings fleece auto insurers out of billions of dollars a year by billing for unneeded treatmentof phantom injuries. Usually these are bogus soft-tissue injuries such as sore backs or whiplash, whichare difficult to medically identify and dispute. Hotspot states– Drivers in Lawrence , MA— the “worst hotbed of fraudulent claims” — have saved more than 68million; Larger chiropractors in Lawrence have decreased in both clinic counts and billings by up to 90percent. High-volume physical therapy clinics (billings exceeding 100,000 annually) have beeneliminated, and attorney involvement in PIP claims has tm#.VfreKRFVhBcCopyright 2015 Oracle and/or its affiliates. All rights reserved. 4
People's Attitudes About FraudConsumers Nearly one of four Americans say it’s ok to defraud insurers–Some 8 percent say it’s “quite acceptable” to bilk insurers, while 16 percent say it’s “somewhatacceptable.”–About one in 10 people agree it’s ok to submit claims for items that aren’t lost or damaged, or forpersonal injuries that didn’t occur.–Two of five people are “not very likely” or “not likely at all” to report someone who ripped of aninsurer. Accenture Ltd.(2003) Nearly one of 10 Americans would commit insurance fraud if they knew they could getaway with it. Nearly three of 10 Americans (29 percent) wouldn't report insurance scams committedby someone they know. Progressive Insurance (2001)Copyright 2015 Oracle and/or its affiliates. All rights reserved.
American Society of Certified Fraud Examiners20 Ways to Detect Fraud1. Unusual BehaviorThe perpetrator will often display unusual behavior, that when taken as a whole is a strong indicator of fraud. The fraudster may not ever take avacation or call in sick in fear of being caught. He or she may not assign out work even when overloaded. Other symptoms may be changes inbehavior such as increased drinking, smoking, defensiveness, and unusual irritability and suspiciousness.2. ComplaintsFrequently tips or complaints will be received which indicate that a fraudulent action is going on. Complaints have been known to be some ofthe best sources of fraud and should be taken seriously. Although all too often, the motives of the complainant may be suspect, the allegationsusually have merit that warrant further investigation.3. Stale Items in ReconciliationsIn bank reconciliations, deposits or checks not included in the reconciliation could be indicative of theft. Missing deposits could mean theperpetrator absconded with the funds; missing checks could indicate one made out to a bogus payee.4. Excessive VoidsVoided sales slips could mean that the sale was rung up, the payment diverted to the use of the perpetrator, and the sales slip subsequentlyvoided to cover the theft.5. Missing DocumentsDocuments which are unable to be located can be a red flag for fraud. Although it is expected that some documents will be misplaced, theauditor should look for explanations as to why the documents are missing, and what steps were taken to locate the requested items. All toooften, the auditors will select an alternate item or allow the auditee to select an alternate without determining whether or not problem exists.6. Excessive Credit MemosSimilar to excessive voids, this technique can be used to cover the theft of cash. A credit memo to a phony customer is written out, and thecash is taken to make total cash pyright 2015 Oracle and/or its affiliates. All rights reserved. http://www.auditnet.org/testing 20 ways.htm
Data, data everywhereGrowth of Data Exponentially Greaterthan Growth of Data Analysts!Data Analysis platformsrequirements: Be extremely powerful andhandle large data volumes Be easy to learn Be highly automated & conomist-data-data-everywhere.pdfCopyright 2016 Oracle and/or its affiliates. All rights reserved.Oracle Confidential –
Analytics Data Warehouse Hadoop Platform Sprawl– More Duplicated Data– More Data Movement Latency– More Security challenges– More Duplicated Storage– More Duplicated Backups– More Duplicated Systems– More Space and PowerCopyright 2014 Oracle and/or its affiliates. All rights reserved.
Vision Big Data Analytic Platform for the Era of Big Data and Cloud–Make Big Data Analytics Model Discovery Simple Any data size, on any computer infrastructure Any variety of data (structured, unstructured, transactional, geospatial), in anycombination–Make Big Data Analytics Model Deployment Simple As a service, as a platform, as an applicationCopyright 2016 Oracle and/or its affiliates. All rights reserved.9
Oracle’s Advanced AnalyticsFastest Way to Deliver Scalable Enterprise-wide Predictive AnalyticsKey Features Scalable in-Database Hadoop datamining algorithms and R integration Powerful predictive analytics anddeployment platform Drag and drop workflow, R and SQL APIs Data analysts, data scientists &developers Enables enterprise predictive analyticsapplicationsCopyright 2016 Oracle and/or its affiliates. All rights reserved.
Oracle’s Advanced AnalyticsFastest Way to Deliver Scalable Enterprise-wide Predictive AnalyticsTraditional AnalyticsMajor Benefits Data remains in Database & Hadoop Model building and scoring occur in-database Use R packages with data-parallel invocations Leverage investment in Oracle IT Eliminate data duplication Eliminate separate analytical servers Deliver enterprise-wide applicationsOracle Advanced AnalyticsData ImportData MiningModel “Scoring”Data Prep. &TransformationavingsData MiningModel BuildingData Prep &Transformation GUI for Predictive Analytics & code gen R interface leverages database as HPC engineData ExtractionModel “Scoring”Embedded Data PrepModel BuildingData PreparationHours, Days or WeeksCopyright 2016 Oracle and/or its affiliates. All rights reserved.Secs, Mins or Hours
FiservRisk Analytics in Electronic PaymentsObjectives Prevent 200M in losses every year using data tomonitor, understand and anticipate fraudSolution “When choosing the tools for fraud management, speed is acritical factor. Oracle Advance Analytics provided a fast andflexible solution for model building, visualization and integrationwith production processes.”– Miguel Barrera, Director of Risk Analytics, Fiserv Inc.– Julia Minkowski, Risk Analytics Manager, Fiserv Inc . We installed OAA analytics for model developmentduring 2014 When choosing the tools for fraud management, speedis a critical factor OAA provided a fast and flexible solution for modelbuilding, visualization and integration with productionprocessesOracle Advanced Analytics3 monthsto run & deployLogisticRegression(using SAS)1 monthto estimate anddeploy Trees andGLMCopyright 2016 Oracle and/or its affiliates. All rights reserved.1 week toestimate, 1week to installrulesin online application1 day to estimate anddeployTrees GLM models(using Oracle AdvancedAnalytics)
Ease of DeploymentData Miner Survey 2016 by Rexer AnalyticsWhile 6 out 10 data miners report the data is available for analysis within days ofcapture, the time to deploy the models takes substantially longer. For 60% of therespondents the deployment time will range between 3 weeks and 1year.Everyoneforgets aboutdeployment –but is mostimportantcomponent!Copyright 2016 Oracle and/or its affiliates. All rights reserved.
UK National Health ServiceCombating Healthcare FraudObjectives Use new insight to help identify cost savings and meet goals Identify and prevent healthcare fraud and benefit eligibilityerrors to save costs Leverage existing data to transform business and productivity “Oracle Advanced Analytics’ data mining capabilities and OracleExalytics’ performance really impressed us. The overall solution isvery fast, and our investment very quickly provided value. We cannow do so much more with our data, resulting in significantsavings for the NHS as a whole”– Nina Monckton, Head of Information Services,NHS Business Services AuthoritySolution Identified up to GBP100 million (US 156 million) potentiallysaved through benefit fraud and error reduction Used anomaly detection to uncover fraudulent activity wheresome dentists split a single course of treatment into multipleparts and presented claims for multiple treatments Analyzed billions of records at one time to measure longerterm patient journeys and to analyze drug prescribing patternsto improve patient careOracle Exadata DatabaseMachineOracle AdvancedAnalyticsCopyright 2016 Oracle and/or its affiliates. All rights reserved.Oracle Exalytics In-MemoryMachineOracle Endeca InformationDiscoveryOracle Business Intelligence EE
Oracle’s Advanced AnalyticsMultiple interfaces across platforms — SQL, R, GUI, Dashboards, AppsUsersR programmersR ClientData & Business Analysts Business Analysts/MgrsSQL Developer/Oracle Data MinerOBIEEDomain End ibutedalgorithmsOracle Database Enterprise EditionOracle Advanced Analytics - Database OptionSQL Data Mining & Analytic Functions R Integrationfor Scalable, Distributed, Parallel in-Database ML ExecutionOracle CloudCopyright 2016 Oracle and/or its affiliates. All rights reserved.Oracle Database12c
Oracle Advanced Analytics Database EvolutionAnalytical SQL in the Database New algorithms (EM,PCA, SVD) Predictive Queries SQLDEV/Oracle DataMiner 4.0 SQL script ODM 11g & 11gR2 addsgeneration and SQLAutoDataPrep (ADP), text Query node (R integration)mining, perf. improvements OAA/ORE 1.3 1.4 SQLDEV/Oracle Data Miner adds NN, Stepwise, Oracle Data Mining3.2 “work flow” GUIscalable R algorithms10gR2 SQL - 7 newlaunched Oracle Adv. AnalyticsSQL dm algorithms Integration with “R” andfor Hadoop Connector Oracle Data Mining and new Oracle Data introduction/addition oflaunched with Oracle acquiresMiner“Classic”9.2i launched – 2Oracle R Enterprisescalable BDAThinking Machinewizards driven GUIalgorithms (NB Product renamed “Oracle algorithmsCorp’s dev. team and AR) via Java SQL statistical 7 Data Mining “Darwin” dataAdvanced Analytics (ODM functionsintroducedAPI“Partners”ORE)mining software199819992002200420052008Copyright 2016 Oracle and/or its affiliates. All rights reserved.20112014
You Can Think of Oracle’s Advanced Analytics Like This Traditional SQLOracle Advanced Analytics - SQL &– “Human-driven” queries– Domain expertise– Any “rules” must be defined andmanagedSQL Queries– SELECT– DISTINCT– Automated knowledge discovery, modelbuilding and deployment– Domain expertise to assemble the “right”data to mine/analyze Analytical SQL “Verbs”– PREDICT– DETECT– AGGREGATE– CLUSTER– WHERE– CLASSIFY– AND OR– REGRESS– GROUP BY– PROFILE– ORDER BY– IDENTIFY FACTORS– RANK– ASSOCIATECopyright 2016 Oracle and/or its affiliates. All rights reserved.
Oracle Advanced Analytics—On Premise or Cloud100% Compatibility Enables Easy Coexistence and MigrationCoExistence and MigrationSame ArchitectureOn-PremiseSame AnalyticsOracle CloudSame StandardsTransparently move workloads and analytical methodologies betweenOn-premise and public cloudCopyright 2016 Oracle and/or its affiliates. All rights reserved.18
Oracle’s Advanced AnalyticsIn-Database Data Mining Algorithms*—SQL &Classification Decision Tree Logistic Regression (GLM) Naïve Bayes Support Vector Machine (SVM) Random Forest& GUI AccessClusteringPredictive Queries Hierarchical k-Means Clustering Orthogonal Partitioning Clustering Regression Expectation-Maximization Anomaly Detection Feature ExtractionAttribute ImportanceFeature Extraction & Creation Minimum Description Length Nonnegative Matrix Factorization Unsupervised pair-wise KL div. Principal Component AnalysisA1 A2 A3 A4 A5A6 A7Regression Multiple Regression (GLM) Support Vector Machine (SVM) Linear Model Generalized Linear Model Multi-Layer Neural Networks Stepwise Linear RegressionAnomaly Detection 1 Class Support Vector MachineTime Series Single & Double Exp. Smoothing Singular Value DecompositionMarket Basket Analysis Apriori – Association RulesOpen Source R Algorithms Ability to run any R package viaEmbedded R mode* supports partitioned models, text miningCopyright 2016 Oracle and/or its affiliates. All rights reserved.
Oracle Advanced AnalyticsHow Oracle R Enterprise Compute Engines WorkOracle Database 12cOther RpackagesR- SQLOracle R Enterprise (ORE) packagesResults1R- SQL Transparency “Push-Down” R language for interaction with the database R-SQL Transparency Framework overloads Rfunctions for scalable in-database execution Function overload for data selection,manipulation and transforms Interactive display of graphical results andflow control as in standard R Submit user-defined R functions forexecution at database server under controlof Oracle Database2RResultsR EngineOracle R Enterprise packages3In-Database Adv Analytical SQL Functions 15 Powerful data mining algorithms(regression, clustering, AR, DT, etc. Run Oracle Data Mining SQL data miningfunctioning (ORE.odmSVM, ORE.odmDT, etc.) Speak “R” but executes as proprietary indatabase SQL functions—machine learningalgorithms and statistical functions Leverage database strengths: SQL parallelism,scale to large datasets, security Access big data in Database and Hadoop viaSQL, R, and Big Data SQLOther RpackagesEmbedded R Package Callouts R Engine(s) spawned by Oracle DB fordatabase-managed parallelism ore.groupApply high performance scoring Efficient data transfer to spawned Rengines Emulate map-reduce style algorithms andapplications Enables production deployment andautomated execution of R scriptsCopyright 2016 Oracle and/or its affiliates. All rights reserved.
Data Mining & Anomaly Detection ConceptsCopyright 2016 Oracle and/or its affiliates. All rights reserved.
What is Data Mining & Predictive Analytics?Automatically sifting through large amounts of data tocreate models that find previously hidden patterns,discover valuable new insights and make predictions Identify most important factor (Attribute Importance) Predict customer behavior (Classification) Predict or estimate a value (Regression) Find profiles of targeted people or items (Decision Trees) Segment a population (Clustering) Find fraudulent or “rare events” (Anomaly Detection) Determine co-occurring items in a “baskets” (Associations)Copyright 2016 Oracle and/or its affiliates. All rights reserved.A1 A2 A3 A4 A5 A6 A7
Data Mining ProvidesBetter Information, Valuable Insights and PredictionsLease Churnersvs. Loyal CustomersSegment #3IF CUST MO 7 AND INCOME 175K, THENPrediction Lease Churner,Confidence 83%Support 6/39Insight & PredictionSegment #1IF CUST MO 14 AND INCOME 90K, THEN Prediction LeaseChurnerConfidence 100%Support 8/39Customer MonthsSource: Inspired from Data Mining Techniques: For Marketing, Sales, and Customer Relationship Management by Michael J. A. Berry, Gordon S. LinoffCopyright 2016 Oracle and/or its affiliates. All rights reserved.
Data Mining When Lack ExamplesBetter Information, Valuable Insights and PredictionsCell Phone Fraudvs. Loyal Customers?Customer MonthsSource: Inspired from Data Mining Techniques: For Marketing, Sales, and Customer Relationship Management by Michael J. A. Berry, Gordon S. LinoffCopyright 2015 Oracle and/or its affiliates. All rights reserved.
Predictive Analytics & Data MiningFinding Rare and Unusual Records in Large Datasets Finding needlesin haystacks. Look for what’sdifferent unlocks-the-big-potential-of-big-data/Copyright 2014 Oracle and/or its affiliates. All rights reserved.
Challenge: Finding Anomalies Consideringmultiple attributesX1X1 Taken alone, mayseem “normal” Taken collectively,a record mayappear to beanomalous Look for what is“different”X2X2X3X4X3X4Copyright 2015 Oracle and/or its affiliates. All rights reserved.
A Real Fraud ExampleMy credit card statement—Can you see the fraud?May 221:14 PMMay 227:32 PMGas Station? June 14 2:05 PMJune 14 2:06 PMJune 15 11:48 AMJune 15 11:49 AMMay 286:31 PMMay 298:39 PMJune 16 11:48 AMJune 16 11:49 AMAll same 75 amount?FOODWINEMonaco CaféWine Bistro 127.38 28.00MISCMISCMISCMISCWINEFOODMISCMISCMobil MartMobil MartMobil MartMobil MartActon ShopCrossroadsMobil MartMobil Mart 75.00 75.00 75.00 75.00 31.00 128.14 75.00 75.00Copyright 2015 Oracle and/or its affiliates. All rights reserved. Monaco?Pairs of 75?
“Essentially, all models are wrong, but some are useful.”– George Box(One of the most influential statisticians of the 20th centuryand a pioneer in the areas of quality control, time seriesanalysis, design of experiments and Bayesian inference.)Copyright 2015 Oracle and/or its affiliates. All rights reserved.
Start with a Business Problem StatementClearly Define Problem“If I had an hour to solve aproblem I'd spend 55 minutesthinking about the problem and 5minutes thinking aboutsolutions.”― Albert EinsteinCopyright 2015 Oracle and/or its affiliates. All rights reserved.
More Data Variety—Better Predictive Models Increasing sources ofrelevant data can boostmodel accuracy100%Naïve Guess orRandomRespondersModel with “Big Data” andhundreds -- thousands of inputvariables including: Demographic data Purchase POS transactionaldata “Unstructured data”, text &comments Spatial location data Long term vs. recent historicalbehavior Web visits Sensor data etc.100%Model with 20 variablesModel with 75 variablesModel with 250 variables0%Population SizeCopyright 2015 Oracle and/or its affiliates. All rights reserved.
Multiple Data Sources/Types with Predictive ModelingEase of Deployment through SQL Script GenerationTransactionalPOS dataSQL Joins and arbitrary SQLtransforms & queries – power of SQLGenerates SQL scriptsfor deploymentInline predictivemodel toaugment inputdataUnstructured dataalso mined byalgorithmsConsider: Demographics Past purchases Recent purchases Customer comments & tweetsCopyright 2016 Oracle and/or its affiliates. All rights reserved.
Tax Noncomplaince Audit SelectionTwo Example Approaches - There are many possible more! Anomaly Detection– Build 1-Class Support VectorMachine (SVM) models on “normalor compliant” tax submissions Unsupervised machine learning whenfew know examples on which to traine.g. 2%– Build Decision Tree models forclassification of Noncompliant taxsubmissions (yes/no) based onhistorical 2011 data Supervised machine learning approachwhen many known examples of targetclasses are available oh which to trainCopyright 2015 Oracle and/or its affiliates. All rights reserved.
SQL Developer/Oracle Data Miner GUIAnomaly Detection—Simple Conceptual WorkflowTrain on “normal” recordsApply model and sort onlikelihood to be “different”Copyright 2015 Oracle and/or its affiliates. All rights reserved.
Copyright 2015 Oracle and/or its affiliates. All rights reserved.
Copyright 2015 Oracle and/or its affiliates. All rights reserved.
Copyright 2015 Oracle and/or its affiliates. All rights reserved.
Copyright 2015 Oracle and/or its affiliates. All rights reserved.
Copyright 2015 Oracle and/or its affiliates. All rights reserved.
Copyright 2015 Oracle and/or its affiliates. All rights reserved.
Copyright 2015 Oracle and/or its affiliates. All rights reserved.
Copyright 2015 Oracle and/or its affiliates. All rights reserved.
Copyright 2015 Oracle and/or its affiliates. All rights reserved.
Copyright 2015 Oracle and/or its affiliates. All rights reserved.
Copyright 2015 Oracle and/or its affiliates. All rights reserved.
Copyright 2015 Oracle and/or its affiliates. All rights reserved.
Copyright 2015 Oracle and/or its affiliates. All rights reserved.
Copyright 2015 Oracle and/or its affiliates. All rights reserved.
Fraud Prediction DemoAutomated In-DB Analytical Methodologydrop table CLAIMS SET;exec dbms data mining.drop model('CLAIMSMODEL');create table CLAIMS SET (setting name varchar2(30), setting value varchar2(4000));insert into CLAIMS SET values ('ALGO NAME','ALGO SUPPORT VECTOR MACHINES');insert into CLAIMS SET values ('PREP AUTO','ON');commit;begindbms data mining.create model('CLAIMSMODEL', 'CLASSIFICATION','CLAIMS', 'POLICYNUMBER', null, 'CLAIMS SET');end;/-- Top 5 most suspicious fraud policy holder claimsselect * from(select POLICYNUMBER, round(prob fraud*100,2) percent fraud,rank() over (order by prob fraud desc) rnk from(select POLICYNUMBER, prediction probability(CLAIMSMODEL, '0' using *) prob fraudfrom CLAIMSwhere PASTNUMBEROFCLAIMS in ('2to4', 'morethan4')))where rnk 5order by percent fraud desc;POLICYNUMBERPERCENT 274964.172344063.22365463.141265062.365Automated Monthly “Application”! Justadd:CreateView CLAIMS2 30AsSelect * from CLAIMS2Where mydate SYSDATE – 30Time measure: set timing on;Copyright 2015 Oracle and/or its affiliates. All rights reserved.
Financial Sector/Accounting/ExpensesAnomaly DetectionSimple Fraud Detection Methodology—1-Class SVMMore Sophisticated Fraud Detection Methodology—Clustering 1-Class SVMCopyright 2015 Oracle and/or its affiliates. All rights reserved.
Multiple Approaches To Detect Potential Fraud1. Anomaly Detection (1-Class SVM) Add feedback loop to purify the input training data over time andimprove model performance2. Classification IF you have a lot of examples (25% or more) of fraud on which to train/learn3. Clustering 4. Find records that don’t high very high probability to fit any particular cluster and/or lie in theoutlier/edges of the clustersHybrid of #3 and then #1Pre-cluster the records to create “similar” segments and then apply anomaly detection models foreach cluster5. Panel of Experts i.e. 3 out of 5 models predict possibly anomalous above 40% or any 1 out of N models considers thisrecord unusualCopyright 2015 Oracle and/or its affiliates. All rights reserved.
TurkcellCombating Communications FraudObjectives Prepaid card fraud—millions of dollars/year Extremely fast sifting through huge datavolumes; with fraud, time is moneySolution “Turkcell manages 100 terabytes of compressed data—or onepetabyte of uncompressed raw data—on Oracle Exadata. WithOracle Data Mining, a component of the Oracle AdvancedAnalytics Option, we can analyze large volumes of customer dataand call-data records easier and faster than with any other tooland rapidly detect and combat fraudulent phone use.”– Hasan Tonguç Yılmaz, Manager, Turkcell İletişim Hizmetleri A.Ş. Monitor 10 billion daily call-data records Leveraged SQL for the preparation—1 PB Due to the slow process of moving data, TurkcellIT builds and deploys models in-DB Oracle Advanced Analytics on Exadata forextreme speed. Analysts can detect fraudpatterns almost immediatelyOracle Advanced AnalyticsIn-Database Fraud ModelsExadataCopyright 2015 Oracle and/or its affiliates. All rights reserved.
Big Data SQLPush down SQL predicts to storage layersCopyright 2015 Oracle and/or its affiliates. All rights reserved.
Introducing Oracle Big Data SQLMassively Parallel SQL Query across Oracle, Hadoop and NoSQLSQLSQLSmall data subsetquickly returnedOffload Query toData NodesdatasubsetHadoop & NoSQLOffload Query toExadata Storage ServersOracle Database 12cCopyright 2015 Oracle and/or its affiliates. All rights reserved. 53
Manage and Analyze All Data—SQL & Oracle Big Data SQLOracle’s Advanced AnalyticsOracle Big Data ApplianceOracle Database 12cSQL / RJSONStructured and Unstructured Data Reservoir JSON data HDFS / Hive NoSQL Spatial and Graph data Image and Video data Social MediaStore business-critical data in Oracle Customer data Transactional data Unstructured documents, comments Spatial and Graph data Image and Video data Social MediaData analyzed via SQL / R / GUI R Clients SQL Clients Oracle Data MinerCopyright 2016 Oracle and/or its affiliates. All rights reserved.54
Getting startedCopyright 2014 Oracle and/or its affiliates. All rights reserved.
OAA Links and Resources Oracle Advanced Analytics Overview:– OAA presentation— Big Data Analytics in Oracle Database 12c With Oracle Advanced Analytics & Big Data SQL– Big Data Analytics with Oracle Advanced Analytics: Making Big Data and Analytics Simple white paper on OTN– Oracle Internal OAA Product Management Wiki and Workspace YouTube recorded OAA Presentations and Demos:– Oracle Advanced Analytics and Data Mining at the YouTube Movies(6 OAA “live” Demos on ODM’r 4.0 New Features, Retail, Fraud, Loyalty, Overview, etc.) Getting Started:– Link to Getting Started w/ ODM blog entry– Link to New OAA/Oracle Data Mining 2-Day Instructor Led Oracle University course.– Link to OAA/Oracle Data Mining 4.0 Oracle by Examples (free) Tutorials on OTN– Take a Free Test Drive of Oracle Advanced Analytics (Oracle Data Miner GUI) on the Amazon Cloud– Link to OAA/Oracle R Enterprise (free) Tutorial Series on OTN Additional Resources:– Oracle Advanced Analytics Option on OTN page– OAA/Oracle Data Mining on OTN page, ODM Documentation & ODM Blog– OAA/Oracle R Enterprise page on OTN page, ORE Documentation & ORE Blog– Oracle SQL based Basic Statistical functions on OTN– BIWA Summit’16, Jan 26-28, 2016 – Oracle Big Data & Analytics User Conference @ Oracle HQ Conference CenterCopyright 2014 Oracle and/or its affiliates. All rights reserved.
Hands-on-LabsCustomer stories, told by the customersEducational sessions by Practitioners and Direct from DevelopersOracle Keynote presentationsPresentations covering: Advanced Analytics, Big Data, Business Intelligence,Cloud, Data Warehousing and Integration, Spatial and Graph, SQL Networking with product management and development professionalsCopyright 2014 Oracle and/or its affiliates. All rights reserved.
Copyright 2014 Oracle and/or its affiliates. All rights reserved.
-Fraud accounts for 5-10 percent of claims costs for U.S. and Canadian insurers. Nearly one-third of insurers (32 percent) say fraud was as high as 20 percent of claims costs; -About 35 percent say fraud costs their companies 5-10 percent of claim volume. More than 30 percent say fraud losses cost 10-20 percent of claim volume;
Oracle e-Commerce Gateway, Oracle Business Intelligence System, Oracle Financial Analyzer, Oracle Reports, Oracle Strategic Enterprise Management, Oracle Financials, Oracle Internet Procurement, Oracle Supply Chain, Oracle Call Center, Oracle e-Commerce, Oracle Integration Products & Technologies, Oracle Marketing, Oracle Service,
In-Database Analytics: Predictive Analytics, Oracle Exadata and Oracle Business Intelligence Charlie Berger Sr. Director Product Management, Data Mining and Advanced Analytics . 12 years ―stem celling analytics‖ into Oracle Designed advanced analytics into database kernel to leverage relational
Types of economic crime/fraud experienced Customer fraud was introduced as a category for the first time in our 2018 survey. It refers to fraud committed by the end-user and comprises economic crimes such as mortgage fraud, credit card fraud, claims fraud, cheque fraud, ID fraud and similar fraud types. Source: PwC analysis 2
Types of economic crime/fraud experienced Customer fraud was introduced as a category for the first time in our 2018 survey. It refers to fraud committed by the end-user and comprises economic crimes such as mortgage fraud, credit card fraud, claims fraud, cheque fraud, ID fraud and similar fraud types. Source: PwC analysis 2
Oracle is a registered trademark and Designer/2000, Developer/2000, Oracle7, Oracle8, Oracle Application Object Library, Oracle Applications, Oracle Alert, Oracle Financials, Oracle Workflow, SQL*Forms, SQL*Plus, SQL*Report, Oracle Data Browser, Oracle Forms, Oracle General Ledger, Oracle Human Resources, Oracle Manufacturing, Oracle Reports,
Bruksanvisning för bilstereo . Bruksanvisning for bilstereo . Instrukcja obsługi samochodowego odtwarzacza stereo . Operating Instructions for Car Stereo . 610-104 . SV . Bruksanvisning i original
Card Fraud 11 Unauthorised debit, credit and other payment card fraud 12 Remote purchase (Card-not-present) fraud 15 Counterfeit Card Fraud 17 Lost and Stolen Card Fraud 18 Card ID theft 20 Card not-received fraud 22 Internet/e-commerce card fraud los
Advanced Replication Option, Database Server, Enabling the Information Age, Oracle Call Interface, Oracle EDI Gateway, Oracle Enterprise Manager, Oracle Expert, Oracle Expert Option, Oracle Forms, Oracle Parallel Server [or, Oracle7 Parallel Server], Oracle Procedural Gateway, Oracle Replication Services, Oracle Reports, Oracle
