Oracle Machine Learning & Advanced Analytics

Transcription

1 Oracle Machine Learning & Advanced Analytics Data Management Platforms Move the Algorithms; Not the Data! Detlef E. Schröder Master Principal Sales Consultant Machine Learning, AI and Cognitive Analytics

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 Oracle s Machine Learning & Data Management Platforms Observations Machine learning, predictive analytics & AI have become must-have requirements Enterprises whose data science teams most rapidly extract predictions and insights win Separate islands for data management and data science just don t work Conclusions Need to evolve towards combined data management + advanced analytics environ that can essentially to store and think about data Must operationalize ML methodologies, insights and predictions throughout enterprise 3

4 Oracle s Machine Learning & Adv. Analytics Algorithms CLASSIFICATION Naïve Bayes Logistic Regression (GLM) Decision Tree Random Forest Neural Network Support Vector Machine Explicit Semantic Analysis CLUSTERING Hierarchical K-Means Hierarchical O-Cluster Expectation Maximization (EM) ANOMALY DETECTION One-Class SVM TIME SERIES State of the art forecasting using Exponential Smoothing. Includes all popular models e.g. Holt-Winters with trends, seasons, irregularity, missing data 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 REST APIs for deployment

5 Multiple Data Scientist User Roles Supported Oracle s Machine Learning/Advanced Analytics Additional relevant data and engineered features Historical data Assembled historical data Sensor data, Text, unstructured data, transactional data, spatial data, etc. Oracle Database 12c Historical or Current Data to be scored for predictions Predictions & Insights DBAs Application Developers R Users, Data Scientists OML Notebook Users Data Analysts, Citizen Data Scientists

6 OAA Model Build and Real-time SQL Apply Prediction Simple SQL Syntax ML Model Build (PL/SQL) begin dbms_data_mining.create_model('buy_insur1', 'CLASSIFICATION', 'CUST_INSUR_LTV', 'CUST_ID', 'BUY_INSURANCE', CUST_INSUR_LTV_SET'); end; / Model Apply (SQL query) Select prediction_probability(buy_insur1, 'Yes' USING 3500 as bank_funds, 825 as checking_amount, 400 as credit_balance, 22 as age, 'Married' as marital_status, 93 as MONEY_MONTLY_OVERDRAWN, 1 as house_ownership) from dual;

7 Manage and Analyze All Your Data Data Scientists, R Users, Citizen Data Scientists Architecturally, Many Options and Flexibility SQL / R Object Store Big Data SQL / R Boil down the Data Lake Engineered Features Derived attributes that reflect domain knowledge key to best models e.g.: Counts Totals Changes over time 9

8 OAA Algorithm Performance Algorithm Time (sec.) Number of Attributes SVM SGD Solver 83s 900 GLM Classification 180s 9000 SVM IPM Solver 811s 900 GLM Regression 59s 900 K-Means 168s 9000 In-memory 640 million rows, Airline On-Time dataset SPARC M8-2 hardware Courtesy of the SPARC Performance Team Copyright 2018 Oracle and/or its affiliates. All rights reserved.

9 Time (sec.) OAA Algorithm Scalability: Rows and Parallelism Random Forest Row Count (M records) X6-2 hardware Benchmarks from Oracle Labs, Systems Research Group Copyright 2018 Oracle and/or its affiliates. All rights reserved. 11

10 The Core Ingredients of Good Machine Learning Domain Knowledge + Data Machine Learning Algorithms Insights, Predictions Machine Learning Algorithms A1 A2 A3 A4 A5 A6 A7 A1 A2 A3 A4 A5 A6 A7 Copyright 2017, Oracle and/or its affiliates. All rights reserved.

11 A1 A2 A3 A4 A5 A6 A7 Most Important Factor in Machine Learning? Deployment!! A Thinking Database Machine Learning Algorithms Copyright 2017, Oracle and/or its affiliates. All rights reserved.

12 Current Release Product Details

13 ADWC + Oracle Machine Learning Notebooks Developer Tools Data Autonomous Warehouse Data Services Warehouse Cloud (EDWs, DW, departmental marts and sandboxes) Service Management Built-in Access Tools Analytics Oracle SQL Developer Data Integration Services Oracle Exadata Cloud Service Oracle Database Cloud Service Service Console Express Cloud Service Oracle Machine Learning Oracle Analytics Cloud Oracle Data Integration Platform Cloud Autonomous Database Cloud 3 rd Party DI on Oracle Cloud Compute Oracle Object Storage Cloud Flat Files and Staging 3 rd Party DI On-premises 15

14 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

15 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

16 Oracle Data Miner GUI Drag and Drop, Workflows, Easy to Use UI 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

17 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 Copyright 2017, Oracle and/or its affiliates. All rights reserved.

18

19

20 Oracle R Enterprise R Language API Component to OAA Machine Learning Functions and SQL Oracle Cloud R language R to SQL transparency layer for push down to SQL for in-db processing Direct access to in-db data ROracle pkg for OCI connectivity Call outs to R pkgs via Embedded R

21 R: Transparency via function overloading Invoke in-database aggregation function Oracle Cloud > aggdata <- aggregate(ontime_s$dest, + by = list(ontime_s$dest), + FUN = length) > class(aggdata) [1] "ore.frame" attr(,"package") [1] "OREbase" > head(aggdata) Group.1 x 1 ABE ABI 34 3 ABQ ABY 10 5 ACK 3 6 ACT 33 Oracle Advanced Analytics ORE Client Packages Transparency Layer Oracle SQL select DEST, count(*) from ONTIME_S group by DEST Oracle Database ONTIME_S In-db Stats Database Server

22 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

23 Newest GA Features Oracle Advanced Analytics 12.2, 18c Oracle Data Miner 17.4 UI ORAAH 2.8 ORE 1.5 Oracle Machine Learning V1

24 Oracle Advanced Analytics 12.2 New Oracle Database Features Significant Performance Improvements for all Algorithms New parallel model build / apply redesigned infrastructure to enable faster new algorithm introduction Scale to larger data volumes found in big data and cloud use cases Unsupervised Feature Selection Unsupervised algorithm for pair-wise correlations (Kullback-Leibler Divergence (KLD)) for numeric & categorical attributes to find highest information containing attributes Association Rules Enhancements Adds calculation of values associated with AR rules such as sales amount to indicate the value of co-occurring items in baskets Can filter input items prior to market basket analysis Partitioned Models Instead of building, naming and referencing 10s or 1000s of models, partitioned models organize and represent multiple models as partitions in a single model entity Partition 1 Partition 2 Partition N

25 Oracle Advanced Analytics 12.2 New Oracle Database Features Explicit Semantic Analysis (ESA) algorithm Useful technique for extracting meaningful, interpretable features; better than LDA English Wikipedia is Text corpus default to equate tokens with human identifiable features and concepts ESA improves text processing, classification, document similarity and topic identification Compare documents that may not even mention same topics e.g. al-qa ida or Osama bin Laden: Document 1 'Senior members of the Saudi royal family paid at least $560 million to Osama bin Laden terror group and the Taliban for an agreement his forces would not attack targets in Saudi Arabia, according to court documents. The papers, filed in a $US3000 billion ($5500 billion) lawsuit in the US, allege the deal was made after two secret meetings between Saudi royals and leaders of al-qa ida, including bin Laden. The money enabled al-qa ida to fund training camps in Afghanistan later attended by the September 11 hijackers. The disclosures will increase tensions between the US and Saudi Arabia.' Document 2 'The Saudi Interior Ministry on Sunday confirmed it is holding a 21-year-old Saudi man the FBI is seeking for alleged links to the Sept. 11 hijackers. Authorities are interrogating Saud Abdulaziz Saud al-rasheed "and if it is proven that he was connected to terrorism, he will be referred to the sharia (Islamic) court," the official Saudi Press Agency quoted an unidentified ministry official as saying. ESA Similarity Score = 0.62

26 New in 18c: Machine Learning and Advanced Analytics Autonomous Data Warehouse Cloud + OML In-DB Machine Learning Algorithms (SQL API) Scalable Random Forests for Classification Scalable Neural Networks for both classification and regression CUR decomposition algorithm for attribute and row importance Time Series: State of the art forecasting 1 using Exponential Smoothing. Includes all popular models e.g. Holt-Winters. Supports trend, damped trend and seasonality. Performs automatic aggregations based on user define time periods or handles irregularly spaced data as direct input. Handles missing values. OML Microservices for applications deployment 1 Gartner paper

27 New in 18c: Oracle Advanced Analytics Oracle R Enterprise New algorithms via ORE API: Expectation Maximization Explicit Semantic Analysis Text mining capabilities OREdplyr support for dplyr functionality using ore.frames R version compatibility upgraded to R Faster ORE launch and connection times OAAgraph for Parallel Graph Analytics

28 Oracle R Advanced Analytics for Hadoop (ORAAH) New Features in ORAAH 2.8 ORAAH analytics as standalone Java library New MPI/Spark-based Algorithms ELM and H-ELM on Spark+MPI Distributed Stochastic PCA & SVD Updated ORAAH GLM and LM algorithms Neural Networks full formula processing in Spark Full formula support and summary for orch.lm2() and orch.glm2 Support for IMPALA and Spark DataFrames Gradient Boosted Trees (Spark MLlib) 30

29 ORAAH: Spark + MPI Combined Performance Spark Strengths Excellent for embarrassingly parallel problems Poor at iterative problems MPI Strengths Excels for highly interconnected problems with thousands of nodes Strong scaling for iterative problems Spark + MPI Combined Performance FASTER! Best of both worlds + 31

30 Why Oracle? Because that s where the data is! Larry Ellison, Executive Chairman and CTO of Oracle Corporation 32

31 Getting Started Oracle ML/AA Resources & Links Oracle Advanced Analytics Overview Information Oracle's Machine Learning and Advanced Analytics 12.2c and Oracle Data Miner 4.2 New Features preso Oracle Advanced Analytics Public Customer References Oracle s Machine Learning and Advanced Analytics Data Management Platforms white paper on OTN Oracle INTERNAL ONLY OAA Product Management Wiki and Beehive Workspace (contains latest presentations, demos, product, etc. information) YouTube recorded Oracle Advanced Analytics Presentations and Demos, White Papers Oracle's Machine Learning & Advanced Analytics 12.2 & Oracle Data Miner 4.2 New Features YouTube video Library of YouTube Movies on Oracle Advanced Analytics, Data Mining, Machine Learning (7+ live Demos e.g. Oracle Data Miner 4.0 New Features, Retail, Fraud, Loyalty, Overview, etc.) Overview YouTube video of Oracle s Advanced Analytics and Machine Learning Getting Started/Training/Tutorials Link to OAA/Oracle Data Miner Workflow GUI Online (free) Tutorial Series on OTN Link to OAA/Oracle R Enterprise (free) Tutorial Series on OTN Link to Try the Oracle Cloud Now! Link to Getting Started w/ ODM blog entry Link to New OAA/Oracle Data Mining 2-Day Instructor Led Oracle University course. Oracle Data Mining Sample Code Examples Additional Resources, Documentation & OTN Discussion Forums 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 Oracle R Advanced Analytics for Hadoop (ORAAH) on OTN Analytics and Data Summit, All Analytics, All Data, No Nonsense. March 12-14, 2019, Redwood Shores, CA Copyright 2016, Oracle and/or its affiliates. All rights reserved.

32 Formerly called the BIWA Summit with the Spatial and Graph Summit. Same great technical content great new name!

33