Transformational Machine Learning Use Cases You Can Deploy Now CON6234

Transcription

1 Transformational Machine Learning Use Cases You Can Deploy Now CON6234 Charlie Berger Sr. Director Product Management Machine Learning, AI and Cognitive Analytics Sebastian Turullols Sr. Director Hardware Development Microelectronics

2 Safe Harbor Statement The following is intended to outline our general product direction. It is intended for information purposes only, and may not be incorporated into any contract. It is not a commitment to deliver any material, code, or functionality, and should not be relied upon in making purchasing decisions. The development, release, and timing of any features or functionality described for Oracle s products remains at the sole discretion of Oracle. 2

3 Today Google Now Provides Tailored Local Updates Get Droid alerts/updates: Local news Local weather Your stated interests Your sports teams National news updates

4

5 Imagine these scenarios Meet old Girlfriend at Coffee Shop Wake up, read Droid alert about meeting a old girlfriend in the coffee shop who will be getting married, but hasn t told anyone yet. Change of address Adopt a dog Facebook pics Tweets Online ring purchase by close contact When you meet your old girlfriend at the coffee shop this morning, act surprised to learn she is getting married

6 The Near Future Big Data, Interconnected World + Machine Learning Datafication of EVERYTHING Digital exhaust GPS Tweets Geo-tags Facebook posts, pics, friends LinkedIn RFID Medical records

7 2001: A Space Odyssey The Dawn of Man scene Our adoption of machine learning and artificial intelligence is about at this stage the BEGINNING!

8 What is Machine Learning, Data Mining, Predictive Analytics? Automatically sift through large amounts of data to find hidden patterns, discover new insights and make predictions Identify most important factor (Attribute Importance) A1 A2 A3 A4 A5 A6 A7 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.

9 CLASSIFYING CUSTOMERS Features Basic Query Basic Analytics Machine Learning Age / Gender Marketing Preferences RFM (Recency, Frequency and Monetary Value): Purchases in the Last 3/6/12 mo. Behavioral Customer Segment Probability to Buy New Product X Known Known Known Unknown Unknown Mail and 1 item / $35 in the last 3 mo Retired Cosmopolitan 2 items / $150 in the last 6 mo Affluential Executive and Facebook 3 items / $75 in the last 3 mo New Home Mom and Google+ 3 items / $225 in the last 12 mo Young Successful startup 31% 45% 55% 21% 72% Mail, and Twitter 9 items / $250 in the last 6 mo Executive product collector Copyright 2017, Oracle and/or its its affiliates. All All rights reserved.

10 ML Model Deployment for Real-Time Scoring Real-Time Scoring, Predictions and Recommendations On-the-fly, single record apply with new data (e.g. from call center) Oracle Cloud Select prediction_probability(clas_dt_1_15, 'Yes' USING 7800 as bank_funds, 125 as checking_amount, 20 as credit_balance, 55 as age, 'Married' as marital_status, 250 as MONEY_MONTLY_OVERDRAWN, 1 as house_ownership) from dual; Call Center Social Media Get Advice Branch Office R Likelihood to respond: Web Mobile

11 Fiserv Risk Analytics in Electronic Payments Objectives Prevent $200M in losses every year using data to monitor, understand and anticipate fraud Solution When choosing the tools for fraud management, speed is a critical factor. Oracle Advance Analytics provided a fast and flexible solution for model building, visualization and integration with production processes. Miguel Barrera, Director of Risk Analytics, Fiserv Inc. Julia Minkowski, Risk Analytics Manager, Fiserv Inc. We installed OAA analytics for model development during 2014 When choosing the tools for fraud management, speed is a critical factor OAA provided a fast and flexible solution for model building, visualization and integration with production processes 3 months to run & deploy Logistic Regression (using SAS) Oracle Advanced Analytics 1 month to estimate and deploy Trees and GLM 1 week to estimate, 1 week to install rules in online application 1 day to estimate and deploy Trees + GLM models (using Oracle Advanced Analytics)

12 Fraud Prediction Demo Automated In-DB Analytical Methodology drop 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; begin dbms_data_mining.create_model('claimsmodel', 'CLASSIFICATION', 'CLAIMS', 'POLICYNUMBER', null, 'CLAIMS_SET'); end; / -- Top 5 most suspicious fraud policy holder claims select * 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_fraud from CLAIMS where PASTNUMBEROFCLAIMS in ('2to4', 'morethan4'))) where rnk <= 5 order by percent_fraud desc; Automated Monthly Application! Just add: Create View CLAIMS2_30 As Select * from CLAIMS2 Where mydate > SYSDATE 30 Time measure: set timing on;

13 1

14 HCM Predictive Workforce Predictive Analytics Applications Human Capital Management Powered by OAA Oracle Advanced Analytics factoryinstalled predictive analytics Employees likely to leave and predicted performance Top reasons, expected behavior Real-time "What if?" analysis Link to Oracle HCM on O.com HCM Predictive Workforce demo

15 HCM Predictive Workforce Predictive Analytics Applications Fusion Human Capital Management Powered by OAA Oracle Advanced Analytics factoryinstalled predictive analytics Employees likely to leave and predicted performance Top reasons, expected behavior Real-time "What if?" analysis Link to Oracle HCM on O.com HCM Predictive Workforce demo

16 Predicting Power Consumption Real-Time In the SPARC M8 Microprocessor Copyright 2016, Oracle and/or its affiliates. All rights reserved. 1

17 Power Prediction Background Power is a precious resource in just about any domain Managing power consumption matters: electricity bill, overloading circuits Power can be managed at many levels Building Data Center Server Processor My work focuses around the processor but these ideas can be applied at other levels or even for totally different ML applications! 1

18 Microprocessor Power Management 101 Applies from a mobile phone CPU to a big iron CPU like the SPARC M8 Limit the instantaneous maximum power draw to avoid tripping circuit breakers or damaging components by overloading them (remember exploding batteries?) Limit the average maximum power to avoid thermal problems Find ways to save power to maximize efficiency / save battery life Before you can implement any of these things you have to know what the power is AND you have to know it far enough in advance to avoid bad things happening 1

19 Microprocessor Power Management Dark Ages Before we knew how to predict power using machine learning Had to always assume the worst case power Lead to engineering overdesign, making servers more expensive Inefficient operation; e.g. fewer servers per rack, lower clock frequency / performance 1

20 Microprocessor Power Management ML Transformation 1 st Transformational Change Using ML to predict power 33% frequency / performance improvement versus previous designs Enabled many new features 2 nd Transformational Change Using Oracle Advanced Analytics flow 95% reduction in effort needed to build and train ML model 100X speedup in training / scoring runtimes 2

21 IP Portfolio Added Power Predictor 2

22 Control System Overview Power Predictor

23 How we predict power SPARC Microprocessors starting with M7 include hardware power predictors that estimate the instantaneous power consumed by an entire core using a few key modeling variables. R and later Oracle Advanced Analytics were used to build this model, including variable selection and training. The most compute intensive task involves selecting ~50 variables from a candidate list of thousands based on about 20GB of training data. 2

24 Performance Challenge Out-of-the box, one round of evaluating a variable addition took 3 hours running single threaded on a single x86 CPU. Since hundreds of rounds needed to complete the predictive model design, prompted a project to accelerate the runtime applied massive parallelization and memory capacity of Oracle SPARC T7-4 Server 2

25 Oracle R Distribution Parallelization Results By moving to T7-4 and through a series of ORD and script coding optimizations to take advantage of the systems massive amount of threads and memory, the team was able to realize a 36X runtime improvement Runtime (minutes) Before 180 After Tuning After Tuning 5 Before

26 Power Prediction Results Achieve <6% error Across all benchmarks 2

27 Oracle Advanced Analytics >100X Improvement Moved to Oracle AA on T8-2 and with minimal effort out-of-the-box were able to achieve much faster runtimes than we got with standard R after a lot of hard work optimizing Runtime (minutes) R Out-of-Box 180 R Tuned 5 OAA Out-of-Box

28 1 minute OAA vs 180 minute R comparison unfair Oracle Advanced Analytics is doing so much more for us in 60 seconds compared to what we had out-of-the-box with R in 2 hours! Automatic optimal best 60 variable selection from candidate pool of 940 R starting point was only a regression of 48+1 variables Runtime (minutes) R Out-of-Box 180 R Tuned 5 OAA Out-of-Box

29 SPARC M8 Processor Based Servers SPARC T8-1 SPARC T8-2 SPARC T8-4 SPARC M8-8 Processors or 4 Up to 8 1 Max Cores Max Threads ,024 2,048 Max Memory 2 1 TB 2 TB 4 TB 8 TB Form Factor 2U 3U 5U Rack / 10U Domaining Logical domains (LDoms) LDoms LDoms LDoms, PDoms 1 (1) Factory configured with one (up to 8 processors) or two (up to 4 processors each) static physical domains (PDoms) (2) Maximum memory capacity is based on 64 GB DIMMs 2

30 Oracle Advanced Analytics 12.2 Model Build Time Performance Unofficial T7-4 (Sparc & Solaris) X5-4 (Intel and Linux) OAA 12.2 Algorithms Rows (Ms) Model Build Time (Secs / Degree of Parallelism) Wow! That s Fast! Attributes Importance s / s / 72 K Means Clustering s / s / 144 Expectation Maximization s / s / 144 Naive Bayes Classification s / s / 72 GLM Classification s / s / 144 GLM Regression s / s / 144 In 24 hours, could build new predictive models for entire United States Population, for 400 attributes, 4 times! Support Vector Machine (IPM solver) s / s / 144 Support Vector Machine (SGD solver) s / s / 72 The way to read their results is that they compare 2 chips: X5 (Intel and Linux) and T7 (Sparc and Solaris). They are measuring scalability (time in seconds) with increase degree of parallelism (dop). The data also has high cardinality Copyright categorical 2016, Oracle columns and/or which its affiliates. translates All rights in reserved. 9K mining attributes (when algorithms require explosion). There are no comparisons to 12.1 and it is fair to say that the 12.1 algorithms could not run on data of this size.

31 Oracle Advanced Analytics 12.2 Model Build Time Performance Unofficial T8-2 (Sparc & Solaris) X6-2 (Intel and Linux) OAA 12.2 Algorithms Rows (Ms) Model Build Time (Secs / Degree of Parallelism) Wow! That s Fast! Attributes Importance s / s / 88 K Means Clustering s / s / 88 Naive Bayes Classification s / s / 88 GLM Classification s / s / 88 GLM Regression s / s / 88 Support Vector Machine (IPM solver) s / s / 88 Support Vector Machine (SGD solver) s / s / 88 The way to read their results is that they compare 2 chips: X5 (Intel and Linux) and T7 (Sparc and Solaris). They are measuring scalability (time in seconds) with increase degree of parallelism (dop). The data also has high cardinality Copyright categorical 2016, Oracle columns and/or which its affiliates. translates All rights in reserved. 9K mining attributes (when algorithms require explosion). There are no comparisons to 12.1 and it is fair to say that the 12.1 algorithms could not run on data of this size.

32 Oracle Database Advanced Analytics Option Machine Learning on SPARC ML training SPARC M7 up to 1.4x faster per core than x86 Predict Train Supervi sed Cluster Model Training: Creating Model from data Oracle Advanced Analytics in Oracle Database 12.2 SPARC M7 faster per core on training 64-bit floating point intensive In-memory 640 million records, Airline On-time dataset SGD (Stochastic Gradient Descent) IPM (Interior Point Method) Attributes M8-2 2-chip M8 per core vs X6-2 GLM Classification s 1.2x SVM SGD Solver s 1.4x SVM IPM Solver s 1.2x GLM Regression s 1.2x K-Means s 1.4x Expectation Maximization s 0.8x Copyright 2016, Oracle and/or its affiliates. All rights reserved. "per core = (server performance)/(server core count)" 32

33 Machine Learning and Advanced Analytics Functionality Overview Copyright 2016, Oracle and/or its affiliates. All rights reserved.

34 Dilbert on Big Data 3

35 Machine Learning/Analytics + Data Warehouse + Hadoop/Spark Platform Sprawl s Inherent Problems Complexity Data Movement Duplicated Data Data Latency Security exposures Duplicated Storage Duplicated Backups Duplicated Systems Dupicated Space and Power

36 Traditional vs. Oracle Machine Learning/Predictive Analtyics Traditional Move the data Don t move the data! 3

37 Traditional vs. Oracle Machine Learning/Predictive Analtyics Traditional Move the data Move the algorithms Simpler, Smarter Data Management + Analytics / Machine Learning Architecture

38 Oracle s Machine Learning/Advanced Analytics Fastest Way to Deliver Enterprise-wide Predictive Analytics Major 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 applications GUI for ML/Predictive Analytics & code gen R interface leverages database as HPC engine Traditional Analytics Data Import Data Mining Model Scoring Data Prep. & Transformation Data Mining Model Building Data Prep & Transformation Data Extraction Hours, Days or Weeks Oracle Advanced Analytics avings Model Scoring Embedded Data Prep Model Building Data Preparation Secs, Mins or Hours Copyright 2016, Oracle and/or its affiliates. All rights reserved.

39 Oracle s Machine Learning/Advanced Analytics Fastest Way to Deliver Scalable Enterprise-wide Predictive Analytics Key Features Parallel, scalable data mining algorithms and R integration In-Database + Hadoop Don t move the data Data analysts, data scientists & developers Drag and drop workflow, R and SQL APIs Extends data management into powerful advanced/predictive analytics platform Enables enterprise predictive analytics deployment + applications

40 Oracle s Machine Learning & Adv. Analytics Algorithms CLASSIFICATION Naïve Bayes Logistic Regression (GLM) Decision Tree Random Forest Neural Network Support Vector Machine CLUSTERING Hierarchical K-Means Hierarchical O-Cluster Expectation Maximization (EM) ANOMALY DETECTION One-Class SVM TIME SERIES Holt-Winters, Regular & Irregular, with and w/o trends & seasonal Single, Double Exp Smoothing REGRESSION Linear Model Generalized Linear Model Support Vector Machine (SVM) Stepwise Linear regression Neural Network LASSO ATTRIBUTE IMPORTANCE Minimum Description Length Principal Comp Analysis (PCA) Unsupervised Pair-wise KL Div CUR decomposition for row & AI ASSOCIATION RULES A priori/ market basket PREDICTIVE QUERIES Predict, cluster, detect, features SQL ANALYTICS SQL Windows, SQL Patterns, SQL Aggregates A1 A2 A3 A4 A5 A6 A7 OAA (Oracle Data Mining + Oracle R Enterprise) and ORAAH combined OAA includes support for Partitioned Models, Transactional, Unstructured, Geo-spatial, Graph data. etc, FEATURE EXTRACTION Principal Comp Analysis (PCA) Non-negative Matrix Factorization Singular Value Decomposition (SVD) Explicit Semantic Analysis (ESA) TEXT MINING SUPPORT Algorithms support text type Tokenization and theme extraction Explicit Semantic Analysis (ESA) for document similarity STATISTICAL FUNCTIONS Basic statistics: min, max, median, stdev, t-test, F-test, Pearson s, Chi-Sq, ANOVA, etc. R PACKAGES CRAN R Algorithm Packages through Embedded R Execution Spark MLlib algorithm integration EXPORTABLE ML MODELS C and Java code for deployment

41 You Can Think of Oracle s Advanced Analytics Like This Traditional SQL Oracle Advanced Analytics - SQL & Human-driven queries Domain expertise Any rules must be defined and managed Automated knowledge discovery, model building and deployment Domain expertise to assemble the right data to mine/analyze SQL Queries Analytical SQL Verbs SELECT DISTINCT AGGREGATE WHERE AND OR GROUP BY ORDER BY RANK + PREDICT DETECT CLUSTER CLASSIFY REGRESS PROFILE IDENTIFY FACTORS ASSOCIATE Oracle Cloud Copyright 2016, Oracle and/or its affiliates. All rights reserved.

42 Oracle Advanced Analytics How Oracle R Enterprise Compute Engines Work Oracle Cloud Other R packages R-> SQL Oracle Database 12c R R Engine Other R packages Oracle R Enterprise (ORE) packages Results Results Oracle R Enterprise packages 1 R-> SQL Transparency Push-Down 2 In-Database Adv Analytical SQL Functions 3 Embedded R Package Callouts R language for interaction with the database R-SQL Transparency Framework overloads R functions for scalable in-database execution Function overload for data selection, manipulation and transforms Interactive display of graphical results and flow control as in standard R Submit user-defined R functions for execution at database server under control of Oracle Database 30+ Powerful data mining algorithms (regression, clustering, AR, DT, etc._ Run Oracle Data Mining SQL data mining functioning (ORE.odmSVM, ORE.odmDT, etc.) Speak R but executes as proprietary indatabase SQL functions machine learning algorithms and statistical functions Leverage database strengths: SQL parallelism, scale to large datasets, security Access big data in Database and Hadoop via SQL, R, and Big Data SQL R Engine(s) spawned by Oracle DB for database-managed parallelism ore.groupapply high performance scoring Efficient data transfer to spawned R engines Emulate map-reduce style algorithms and applications Enables production deployment and automated execution of R scripts Copyright 2016, Oracle and/or its affiliates. All rights reserved.

43 Oracle s Machine Learning/Advanced Analytics Platforms Machine Learning Algorithms Embedded in the Data Management Platforms Analytics Producers Analytics Consumers Data Scientists, R Users, Citizen Data Scientists BI Analysts, Managers Functional Users (HCM, CRM) Data Management + Advanced Analytical Platform Big Data SQL Big Data Cloud Service Oracle Machine Learning Big Data Cloud ORAAH Machine Learning Algorithms, Statistical Functions + R Integration for Scalable, Parallel, Distributed Execution Database Cloud Oracle Machine Learning Database Edition Machine Learning Algorithms, Statistical Functions + R Integration for Scalable, Parallel, Distributed, in-db Execution

44 Manage and Analyze All Your Data Data Scientists, R Users, Citizen Data Scientists Architecturally, Many Options and Flexibility SQL / R Boil down the Data Like Big Data SQL / R Object Store Engineered Features Derived attributes that reflect domain knowledge key to best models e.g: Counts Totals Changes over time 4

45 Why Oracle? Because that s where the data is! Larry Ellison, Executive Chairman and CTO of Oracle Corporation 45

46 Oracle Data Miner workflow UI Oracle SQL Developer extention; Easy to Use for Citizen Data Scientist Easy to use to define analytical methodologies that can be shared SQL Developer Extension Workflow API and generates SQL code for immediate deployment Oracle Cloud

47 Rapidly Build, Evaluate & Deploy Analytical Methodologies Leveraging a Variety of Data Sources and Types SQL Joins and arbitrary SQL transforms & queries power of SQL Transactional POS data Modeling Approaches Inline predictive model to augment input data Unstructured data also mined by algorithms Consider: Demographics Past purchases Recent purchases Comments & tweets Generates SQL scripts and workflow API for deployment

48

49 Oracle Machine Learning Machine Learning Notebook for Autonomous Data Warehouse Cloud Key Features Collaborative UI for data scientists Packaged with Autonomous Data Warehouse Cloud (V1) Easy access to shared notebooks, templates, permissions, scheduler, etc. SQL ML algorithms API (V1) Supports deployment of ML analytics

50

51 Confidential Oracle 51

52