Loading…
  • Sessions appear in the color of their primary track
  • Sessions can be filtered using Products on the right
  • Use the Search bar for more flexibility
See this link for hints on how to search the schedule or sign up for sessions

Sign up or log in to bookmark your favorites and sync them to your phone or calendar.

Machine Learning [clear filter]
Tuesday, March 20
 

11:15am

Oracle Machine Learning & Advanced Analytics: New Features, Cloud & Road Map
Oracle Advanced Analytics 12.2c delivers new features and significant performance gains. OAA new features include an unsupervised feature selection algorithm, ESA algorithm, partitioned models. OAA can now build machine learning models on billions of records in minutes, “score” millions of records even faster and supports real-time model deployment. Integration with R now supports R model registration for in-database processing. Oracle Data Miner adds a workflow Scheduler. ORAAH adds new ML algorithms. Oracle Machine Learning, a new Zeppelin based notebook supports collaborative model building and deployment in Oracle Data Warehouse Clouds. Several customer reference use cases will be presented.

Speakers
avatar for Charlie Berger

Charlie Berger

Senior Director, Product Management, Oracle
Charlie Berger is the Sr. Director of Product Management, Machine Learning, AI and Cognitive Analytics in Oracle Server Technology. Since 1999, he has been responsible for Oracle’s machine learning—starting when Oracle acquired Thinking Machines Corporation where he was VP of... Read More →


Tuesday March 20, 2018 11:15am - 12:05pm
3-Rm 103

1:10pm

MSET Plus Situation Awareness for Big Data Healthcare Prognostic Applications
Situation Awareness (SA) is arguably the best method to extract the highest value from data;  Oracle's KIDS (Knowledge Intensive Data-management Services) is a particularly efficient model for achieving SA.  The Multivariate State Estimation Technique (MSET) is an advanced prognostic pattern recognition method that was originally developed in the 1990's for high-sensitivity prognostic applications in complex safety-critical industries by discovering anomalies with the provably lowest-possible false positives/negatives, and with low resource consumption.  Oracle's new MSET-2 combined with SA solves issues that confuse humans in the loop, and confound the best conventional ML algorithmics. The combination of Oracle MSET-2 and SA achieves a compelling value proposition for Big Data life sciences and healthcare applications, as well as for newly emerging dense-sensor IoT applications and human-in-the-loop supervisory-control applications.

Speakers
avatar for Dieter Gawlick

Dieter Gawlick

Architect, Oracle
With almost 50 years of experience in the IT industry I was seen and contributed to many areas, e.g., databases, transaction processing, workflow, event processing, messaging, and ML. Using ML, data (base) management systems are now able to study the structure of the data values... Read More →
avatar for Kenny  Gross

Kenny Gross

Solutions Architect, Oracle
Kenny C Gross, PhD, is an AI Architect in Oracle's Physical Sciences Research Center in San Diego, CA. Kenny specializes in advanced pattern recognition and prognostic anomaly discovery for Big Data applications in IoT industries, life sciences, and business business-critical data... Read More →


Tuesday March 20, 2018 1:10pm - 2:00pm
4-Rm 104

1:10pm

HOL: Machine Learning 101 with Oracle Data Miner and ADWC's Machine Learning Notebook
Limited Capacity full
Adding this to your schedule will put you on the waitlist.

Learn the fast and way to perform machine learning using SQL Developer 17.2’s Oracle Data Miner drag and drop workflow UI. Learn from multiple experts in the room who will provide 1:1 coaching, guidance and instruction as requested in performing several hands on tutorials. Ask questions, get answers and come away with a comfort level of using Oracle’s machine learning capabilities in your use cases.
Also, try the new Oracle Machine Learning (OML) Zeppelin-based notebook for the Autonomous Data Warehouse Cloud (ADWC). OML extends Oracle’s offerings for data science in the cloud. OML’s collaborative, notebook environment helps data scientists built, share, document and automate data analysis methodologies that run in ADWC. Come learn about how easy it is to use Oracle’s newest SQL notebook technology to access and view data and build and deploy predictive machine learning models.

Speakers
avatar for Charlie Berger

Charlie Berger

Senior Director, Product Management, Oracle
Charlie Berger is the Sr. Director of Product Management, Machine Learning, AI and Cognitive Analytics in Oracle Server Technology. Since 1999, he has been responsible for Oracle’s machine learning—starting when Oracle acquired Thinking Machines Corporation where he was VP of... Read More →
avatar for Karl Rexer

Karl Rexer

President, Rexer Analytics
My company: www.RexerAnalytics.comI started Rexer Analytics in 2002. We're a small data science, predictive modeling & analytic CRM consulting firm. We help clients explore and understand their customers' needs, market to them more effectively, and use data to make better strategic... Read More →
avatar for Tim Vlamis

Tim Vlamis

VP & Analytics Strategist, Vlamis Software Solutions
An Oracle Ace and expert in the visualization of data and the design of business analytics strategies, Tim combines a strong background in the application of Oracle-based business analytics and data mining with extensive experience in business modeling and valuation analysis. Tim... Read More →


Tuesday March 20, 2018 1:10pm - 3:20pm
6-Bldg 500

3:35pm

Customer Analytics with Oracle Advanced Analytics - from reactive to proactive
Long gone are the days when mass mails with the same message and offer were sent to all customers. With the amount of data companies have on their customers together with tools such as Oracle Advanced Analytics a new world of possibilities for personalized and proactive marketing opens up. A company with customer data in an existing datawarehouse built on Oracle databases have a short time to market for an advanced analytics platform using the licensed option of Oracle Advanced Analytics. In this session I will go through the learnings along the way from being reactive to proactive using the whole offering of R together with Oracle Advanced Analytics to empower data scientists and analysts to generate cutting edge customer insights inside the database.

Speakers
avatar for Magnus Perman

Magnus Perman

Senior Consultant / Solution Architect, SIGMA IT Consulting
Magnus is a senior consultant working for the Swedish company SIGMA IT Consulting. Magnus holds a M.Sc. in Computer Science and has over 15 years experience of working with different clients and delivered solutions within the areas of Business Intelligence, Data Warehousing and Analytics... Read More →


Tuesday March 20, 2018 3:35pm - 4:05pm
1-Auditorium

3:35pm

Forecasting the storm recovery resource allocation in electric utility network
A leading cause of power outages in the US is weather driven equipment failure events. Oracle utility customers are seeking machine learning techniques (recommended by the USDOE) to improve real-time risk assessment for critical assets based upon incoming weather forecast. Given an accurate prediction for the location, type, and amount of the storm-damaged equipment, the utility company can position the right number of specialized crews and material resources ahead of time. We develop a novel machine-learning model trained on the history of asset failures and reported weather. Since the weather-reporting stations might be far from the assets and some weather data measurements might be missing, we interpolate the weather conditions at the asset locations using a triangularization function computed with a barycentric coordinates technique implementation. We report performance comparison of multiple machine learning models to recommend the best damage prediction tool.

Speakers
avatar for Kenny  Gross

Kenny Gross

Solutions Architect, Oracle
Kenny C Gross, PhD, is an AI Architect in Oracle's Physical Sciences Research Center in San Diego, CA. Kenny specializes in advanced pattern recognition and prognostic anomaly discovery for Big Data applications in IoT industries, life sciences, and business business-critical data... Read More →
avatar for Andrew Vakhutinsky

Andrew Vakhutinsky

Consulting Member of Technical Staff, Oracle
Andrew Vakhutinsky is a Consulting Member of Technical Staff at Oracle Labs. He has Ph.D. in Operations Research from University of Maryland, College Park, and M.Sc. in Physics and Applied Mathematics from Moscow University of Physics and Technology. Andrew's previous experience includes... Read More →


Tuesday March 20, 2018 3:35pm - 4:05pm
4-Rm 104

4:20pm

Introducing Oracle R Enterprise 1.5.1 New Features
Oracle R Enterprise, a component of the Oracle Advanced Analytics Option, makes the open source R statistical programming language and environment ready for the enterprise and big data. Designed for problems involving both large and small volumes of data, Oracle R Enterprise integrates R with Oracle Database, enabling R users to run R commands and scripts for statistical, machine learning, and graphical analyses on database tables. In this session, we will briefly introduce Oracle R Enterprise, but focus on the new features of Oracle R Enterprise 1.5.1, including:
  • OREdplyr - transparncy layer package based on the popular and powerful dplyr package from the tidyverse
  • OAAgraph - enabling combining Oracle Spatial and Graph PGX with OAA machine learning from a common R interface
  • Explicit Semantic Analysis algorithm - new text analytics capability to extract features based on human curated topics, such as from Wikipedia
  • Partititioned models - automated building and scoring of predictive models based on  data partitions
  • and more...
Join us to see what how you could take your R-based analytics to the next level of functionality, scalability, and performance.

Speakers
avatar for Mark Hornick

Mark Hornick

Director, Oracle
Mark Hornick is a Director for Oracle Advanced Analytics Product Management, focusing on Oracle R Enterprise (ORE), Oracle R Advanced Analytics for Hadoop (ORAAH), and the new Oracle Machine Learning for Python (OML4Py). He works with internal and external customers in the application... Read More →


Tuesday March 20, 2018 4:20pm - 5:10pm
2-Rm 102
 
Wednesday, March 21
 

9:00am

HOL: Using R for Big Data Advanced Analytics, Machine Learning, and Graph
Limited Capacity full
Adding this to your schedule will put you on the waitlist.

Oracle R Enterprise (ORE), a component of the Oracle Advanced Analytics Option, provides a comprehensive, database-centric environment for end-to-end analytical processes in R, enabling immediate deployment to production environments. Entire R scripts can be operationalized in production applications - eliminating the need to port R code. Using ORE with Oracle Database enables R users to transparently analyze and manipulate data in Oracle Database thereby eliminating memory constraints imposed by client R engines. In this hands-on lab, attendees will work with the latest Oracle R Enterprise software, getting experience with the transparency layer, machine learning algorithms, and embedded R execution. Working with the instructors through scripted scenarios, users will understand how R is used in combination with Oracle Database to analyze big data.

Speakers
avatar for Mark Hornick

Mark Hornick

Director, Oracle
Mark Hornick is a Director for Oracle Advanced Analytics Product Management, focusing on Oracle R Enterprise (ORE), Oracle R Advanced Analytics for Hadoop (ORAAH), and the new Oracle Machine Learning for Python (OML4Py). He works with internal and external customers in the application... Read More →


Wednesday March 21, 2018 9:00am - 10:55am
6-Bldg 500

11:10am

Operationalizing Machine Learning
Most data science projects begin with data, “tools” and scripts but fail to get beyond the data scientist. They hit a wall when attempting to “operationalize” the models. Netflix never implemented the algorithm that won the Netflix $1 Million Challenge. This dichotomy between enterprise and algorithms is eliminated when algorithms are built into the data management platforms. By “moving algorithms to the data”, Oracle Database and Big Data Clouds are now data management and advanced analytical platforms. “Robots” can replicate human tasks by capturing best practices discovered in the data and automating that process using machine learning deployed models. Developers use SQL, R and Oracle Data Miner UI to build, evaluate and deploy advanced analytical methodologies. See how to go beyond “tools” to enabling RPA (robotic process automation) applications. Several Oracle “predictive” Applications will be shown as examples._x000D_

Speakers
avatar for Charlie Berger

Charlie Berger

Senior Director, Product Management, Oracle
Charlie Berger is the Sr. Director of Product Management, Machine Learning, AI and Cognitive Analytics in Oracle Server Technology. Since 1999, he has been responsible for Oracle’s machine learning—starting when Oracle acquired Thinking Machines Corporation where he was VP of... Read More →


Wednesday March 21, 2018 11:10am - 12:00pm
2-Rm 102

1:00pm

Using Machine Learning in OBIEE for Predictive Analytics and Actionable BI
This presentation focuses on unlocking the power of Data Science for data-driven decision support. It details the pragmatics of using Machine Learning techniques in OBIEE for actionable BI and Predictive Analytics from a business standpoint. Two industry use cases are presented to illustrate the implementation of the same using OBIEE 12c.

Speakers
avatar for Lakshman Bulusu

Lakshman Bulusu

Consultant, 1967
Lakshman Bulusu is a senior Oracle consultant with 25 years of experience in the fields of Oracle RDBMS, SQL, PL/SQL, EDW/BI/EPM,  Oracle-related Java and Oracle-related R, machine learning, Vertica and Alteryx. As an enterprise level data warehouse and BI solution architect/technical... Read More →


Wednesday March 21, 2018 1:00pm - 1:50pm
2-Rm 102

2:20pm

Anomaly detection and machine learning - with Oracle Management Cloud
The Oracle Management Cloud is a broad platform which has great capabilities on mining data and perform machine learning in order to detect anomalies in your IT systems. In this way you will be able to pro actively detect possible bottlenecks, predict peak loads so you can take the necessary actions to scale your system. In this session it will be explained how to use these features.

Speakers
avatar for Michel Schildmeijer

Michel Schildmeijer

Lead Technologist & Oracle ACE, Qualogy, Netherlands
Having made his start in the pharmacy sector, Michel transitioned to IT in 1996, working on a UNIX TTY terminal-based system and the MUMPS language. He currently works as a solutions architect at Qualogy, with a focus on middleware, application integration, and service-oriented architecture... Read More →


Wednesday March 21, 2018 2:20pm - 3:10pm
1-Auditorium

3:25pm

manufacturing_df.transform().fit()
Real life Manufacturing Data is not like iris or titanic. We cannot just .fit() and .score(). We need to effectively .transform() the data. In this presentation, we will look at the complexity of manufacturing data and various ways to feature engineer manufacturing data to derive meaningful variables to solve manufacturing problems. Specifically we will look at a. Methods to construct machine learning data set for different type of Manufacturing like Lot Controlled, Serial Controlled, Batch Manufacturing, Discrete Manufacturing b. Transformation method of time series data from Machine Sensor Readings c. Various binning transformations on transaction data

Speakers
avatar for Sreeram Hariharan

Sreeram Hariharan

Senior Prinicipal Applications Engineer, Oracle Corp
Application Developer working on Adaptive Intelligent Applications for Manufacturing.


Wednesday March 21, 2018 3:25pm - 4:15pm
6-Bldg 500

4:30pm

Anomaly Detection in Medicare Provider Data using OAAgraph
Graph analysis is an effective methodology in data analysis which considers fine-grained relationships between data entities. This session presents an example of anomaly detection using graph analysis on data stored in Oracle Database with Oracle R Enterprise and the OAAgraph package, using a real-world public data set.
Specifically, we analyze the public information of medical transactions from CMS (United States Center for Medicare and Medicaid Services) for the year 2012. We load this data set as a graph into Oracle Database, and use the OAAgraph package to apply graph analysis algorithms whose results are be visualized using R's ggplot2 visualization package. 
Our analysis successfully identifies suspicious records in the data set -- medical providers who perform procedures far from their specialties. We also discuss techniques how to reduce false positive outcomes. 

Speakers
avatar for Sungpack Hong

Sungpack Hong

Research Director, Oracle Labs
Research Director at Oracle Labs.Leading projects regarding large-scale graph and data analysis -- platforms and applications
avatar for Mark Hornick

Mark Hornick

Director, Oracle
Mark Hornick is a Director for Oracle Advanced Analytics Product Management, focusing on Oracle R Enterprise (ORE), Oracle R Advanced Analytics for Hadoop (ORAAH), and the new Oracle Machine Learning for Python (OML4Py). He works with internal and external customers in the application... Read More →
FM

Francisco Morales

Software Developer, Oracle Labs


Wednesday March 21, 2018 4:30pm - 5:00pm
2-Rm 102
 
Thursday, March 22
 

8:45am

New Machine Learning capabilities: Interacting with Spark DF in ORAAH
The newly redesigned ORAAH (Oracle R Advanced Analytics for Hadoop) brings a complete rewrite of it's I/O model, allowing for the use of a complete in-memory pipeline, from data transformation and loading all the way to Machine Learning models and predictions. In addition to that, a new transparency layer to Impala, plus the option to run HIVE on Spark queries, can keep the data always in-memory across different platforms. A new Extreme Learning Machine algorithm will be introduced, and enhancements on the Logistic and Linear Regression algorithms will increase scalability even more. Benchmarks with the new features will be presented on typical use cases by customers, from predicting flight cancellations and delays to Image Classification.

Speakers
avatar for Marcos Arancibia

Marcos Arancibia

Product Manager, Data Science and Big Data, Oracle
Marcos Arancibia is the Product Mgr for Oracle Data Science and Big Data, working with Machine Learning in the Oracle Database and on Hadoop/Spark clusters. He is charted with developing a comprehensive platform for enabling a new class of analytical workloads encompassing techniques... Read More →


Thursday March 22, 2018 8:45am - 9:35am
1-Auditorium

9:50am

Analytic platform with a hybrid approach of home grown and vendor tools
Adopting any new technology is daunting, in addition to peer pressure, there is also a need to size up as data grows, all without breaking the bank. The original BIWA 2015 presentation was on how any IT shop can build a commodity Hadoop cluster with Dell servers, Redhat Linux, Infiband network cards and Cloudera HDFS. Most of the coding was in Java, and OLH (Oracle Loader for Hadoop) was used to load data into an Oracle 12c in-memory table (presented at OOW15). The expertise of Computer Science faculty, staff and students was used for the full project with vendor support.The group has since enhanced the cluster with SSD (Solid State Drives) and SPARK2, and written Python Spark Machine Learning code to  analyze Gigabyte size aircraft  logs. The visualization of the data using R-Oracle has been planned for the future.

Speakers
AA

Abhinav Arya

Research Intern, Naval Postgraduate School
avatar for Arijit Das

Arijit Das

Research Associate, Naval Postgraduate School
Arijit Das is a computer scientist with BS/MS degrees in Computer Science (MNREC, India & Oregon State University) and an MSEE from University of Nevada Las Vegas. He currently is a research faculty at the Computer Science Department of the Naval Postgraduate School in Monterey, California... Read More →
JZ

Jim Zhou

Researcher, NPS


Thursday March 22, 2018 9:50am - 10:40am
4-Rm 104

10:55am

Oracle & R -- Advanced Analytics on Steroids
The value of Oracle R Enterprise and the ability to use custom R scripts in various Oracle analytics tools cannot be understated. …But how do you use R to maximize your organization’s analytics? From the standard, included scripts to custom scripts, this session will focus on making sure the “secrets” are known about using R scripts in Oracle analytics tools.

Speakers
avatar for Sarah Zumbrum

Sarah Zumbrum

VP BI and Analytics, Accelytics
Sarah Craynon Zumbrum is an Oracle ACE Alumni (Director) currently a Public Sector Enterprise Cloud Architect specializing in Business Intelligence and Analytics for Oracle. She has previously worked in-house as a business intelligence architect and as an EPM consultant, specializing... Read More →


Thursday March 22, 2018 10:55am - 11:45am
1-Auditorium

1:30pm

Using Oracle R Enterprise for Event Registration Modeling and Propensity to Buy
Oracle Marketing Advanced Analytics team has been using Oracle R Enterprise(ORE) for propensity to buy modeling for the past few years. We have recently expanded our use of ORE to event registration. The models allow Oracle to target the right contacts for email marketing for product events. We have shown up to 4X increase in registration rates from model targets over the baseline. The presentation will cover an overview of the results of our modeling as well as some key insights we have learned on how to model using ORE.

Speakers
avatar for Joseph Darschewski

Joseph Darschewski

Sr. Data Scientist, Oracle
Sr Data ScientistOracle Marketing Advanced AnalyticsMS Statistics15+ years experience


Thursday March 22, 2018 1:30pm - 1:55pm
1-Auditorium

1:55pm

Oracle Machine Leaning & Adaptive Intelligent Applications for Manufacturing
In this session learn about Oracle's soon to be released prepackaged "SaaS on PaaS" cloud applications called "Adaptive Intelligent Applications for Manufacturing". This product is built directly on top of several Oracle’s PaaS components to collect, store, and analyze massive amounts of Operational Technology (OT) data coming from shopfloor systems such as MES, quality systems, LIMS, Equipment, Test stations and contextualizes this data with Information Technology (IT) data residing in HCM/CRM/SCM/ERP applications in a single consolidated operational data store and analyzed by applying advanced analytics, data mining/data science, and AI techniques to discover key patterns and correlations from historical data related to manufacturing efficiencies and also provide actionable predictive analytics to improve yield, reduce defects, reduce scrap, minimize cycle times, manufacturing costs, and equipment downtime.

Speakers
avatar for Gopal Ratnam

Gopal Ratnam

Senior Director, Product Management & Strategy, Oracle
TBD


Thursday March 22, 2018 1:55pm - 2:20pm
1-Auditorium

4:05pm

Enhance the Value of Dark Data - Unstructured Text
DarkdataSpot® creates Guidance-Seeking queries to find better answers faster and create efficiencies which ultimately leads to confident decisions that deliver rapid return on investment (ROI). Live Demo: https://www.youtube.com/watch?v=fAorPSVjVYU

Speakers
avatar for Albert Rojas

Albert Rojas

Founder, DarkdataSpot.com
Albert Rojas Enterprise Software Sales Engineer | Big Data | Self Service JPMorgan Chase & Co.University of California, San DiegoGreater New York City Area 500+ 500+ connections


Thursday March 22, 2018 4:05pm - 4:30pm
3-Rm 103
 

Twitter Feed