Andreas Forster / Solution Advisor
June 2013
• Introduction to Predictive Analysis
• Use Cases, Demo & Customers
• Predictive Applications
• High Performance Applications (on SAP HANA)
• SAP Predictive Analysis
• Architecture and Algorithms
• Questions & Answers
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
2
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
3
•
•
•
•
•
•
Some Data Mining Buzzwords
Data Mining
Machine Learning
Artificial Intelligence
Automatic / Semi-automatic
Unknown Correlations, Patterns, Trends
Large Data Analysis
Better understand the past to know more about the future.
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
4
Sense & Respond Predict & Act
Optimization
Predictive
Modeling
What is the best that could happen?
Generic
Predictive
Analytics
Ad Hoc
Reports &
OLAP
What will happen?
Raw
Data
Cleaned
Data
Standard
Reports
Why did it happen?
What happened?
Analytics Maturity
The key is unlocking data to move decision making from sense & respond to predict & act
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
5
Empower the Business
Extend the Business Intelligence competency to Advanced
Analytics
Embed Predictive into Apps and
BI environments
Lend expertise
In-time Actionable Insights
In-memory processing
No data latencies
Big Data ready
Real-time in-memory predictive and next generation visualization and modeling
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
In Context
Relevant to your business
Within the context of your
Industry and LOB scenario
Partner and customer apps
6
• Introduction to Predictive Analysis
• Use Cases, Demo & Customers
• Predictive Applications
• High Performance Applications (on SAP HANA)
• SAP Predictive Analysis
• Architecture and Algorithms
• Questions & Answers
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
7
Business and Industry Use Cases where SAP has helped
Healthcare Insurance
Identify unusual transactions for fraud prevention.
Rate / Score the risk that is to be insured.
Predict likelihood of disease to begin early treatment; identify clinical trial outcomes.
Banking
Identify key behaviors of customers likely to leave the bank; improve credit risk analysis.
Utilities
Forecast demand and usage for seasonal operations; provide anticipated resources.
Government CRM Marketing
Identify potential leads among existing customers and intelligently market to them based on individual preferences and histories
Retail
Product suggestions based on past purchases; inventory planning; selection of store locations based on demographics.
Predict community movement and trends that affect taxing districts; anticipate revenue.
Telco
Forecast demand on system load for capacity planning and customer scale. Reduce customer churn. Keep influencer customers.
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
8
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
9
5,000 events per second loaded onto SAP
HANA (not possible before)
Business Challenges
Increase conversion rates from free paying player
Increase the average revenue per paying player
Decrease churn – keep paying players playing longer
10-30% increase in revenue per year
Technical Challenges
Leverage real-time data processing in SAP HANA and classification algorithms with R integration for SAP HANA to deliver personalized context-relevant offers to players
Analyze vast amounts of historical and transactional data to forecast player behavior patterns
Interactive analysis leading to improved design thinking and game planning data
Benefits
Real-time insights
Per player profitability analysis and increased understanding of player behavior
Increase data volume and processing capabilities to communicate personalized messages to players
“ ”
At Bigpoint in the Battlestar Galactica online game, we have more than 5,000 events in the game per second which we have to load in SAP HANA environment and to work on it to create an individualized game environment to create offers for them. In this co-innovation project with SAP HANA, using Real Time Offer Management
Bigpoint, we hope to increase revenue by 10-30%.
Claus Wagner, Senior Vice President SAP Technology, Bigpoint
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
10
408,000x faster than traditional disk-based systems in a technical PoC
Business Challenges
Reduce delays and minimize the costs associated with new drug discovery by optimizing the process for genome analysis
Improve and speed decision making for hospitals which conduct cancer detection based on DNA sequence matching
216x faster by reducing genome analysis from several days to only 20 minutes making realtime cancer/drug screening possible
Technical Implementation
Leveraged the combination of SAP HANA, R, and Hadoop to store, pre-process, compute, and analyze huge amounts of data
Provide access to breadth of predictive analytics libraries
Benefits
For pharmaceutical companies, provide required new drugs on time and aid identification of “driver mutation” for new drug targets
Able to provide a one stop service including genomic data analysis of cancer patients to support personalized patient therapeutics
“ ”
Our solution is to incorporate SAP HANA along with Hadoop and R to create a single real-time big data platform. With this we have found a way to shorten the genome analysis time from several days down to only 20 minutes.
Yukihisa Kato, CTO and Director of MITSUI KNOWLEDGE INDUSTRY
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
11
• Introduction to Predictive Analysis
• Use Cases, Demo & Customers
• Predictive Applications
• High Performance Applications (on SAP HANA)
• SAP Predictive Analysis
• Architecture and Algorithms
• Questions & Answers
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
12
Unleash the value of Big Data through the power of SAP HANA
• Employ in-database predictive algorithms
• Access 3,500+ open-source algorithms via R integration for SAP HANA
Intuitively design and visualize complex predictive models
• SAP Predictive Analysis software
Bring predictive insight to everyone in the business
• Embed within business applications
• Extend into BI and reports
• Insight into events instantly delivered to dashboards, alerts, and mobile devices
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
13
Customer Revenue Performance
Management
Account Intelligence Predictive Customer Segmentation
*: Predictive seamlessly embedded in applications
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
14
Intuitively design complex predictive models
Read and write from data stored in SAP HANA, Universes, IQ, and other sources
Drag-and-drop visual interface for data selection, preparation, and processing
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
15
Data Visualization and
Sharing
1.
2.
Visualize the model for better understanding
Store the model and result
3.
back to SAP HANA
Share results via PMML and with other BI client tools
Step 4
Data
Visualization and
Sharing
Step1
Data Loading
Step 2
Data Preparation
Data Loading
1.
Understand the business and
2.
identify issues
Load the SAP and non-SAP data into SAP HANA or other source
Data Processing
1.
Define the model via clustering , classification, association, time series, etc.
2.
Run the model
Step 3
Data Processing
Data Preparation
1.
Visualize and examine the
2.
data
Sample, filter, merge, append, apply formulas
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
16
Visualize, discover, and share hidden insights
Advanced visualization designed where you’d expect it – natively from within the modelling tool
Share insights via PMML and with other BI client tools
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
17
• Introduction to Predictive Analysis
• Use Cases, Demo & Customers
• Predictive Applications
• High Performance Applications (on SAP HANA)
• SAP Predictive Analysis
• Architecture and Algorithms
• Questions & Answers
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
18
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
19
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
20
Combine the depth and power of in-memory analytics within SAP HANA with the breadth of R to support a variety of advanced analytic and predictive scenarios
Predictive Analysis Library (PAL)
Native predictive algorithms
In-database processing for powerful and fast results
Quicker implementations
Support for clustering, classification, association, time series etc…
R Integration for SAP HANA
Enables the use of the R open source environment (> 3,500 packages) in the context of the HANA in-memory database
R integration enabled via high performing parallelized connection
R script is embedded within SAP HANA SQL Script
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
21
SAP Predictive
Analysis
SAP and Custom
Applications
Business
Intelligence
Clients
SAP HANA Studio
SAP HANA Platform
Predictive Analysis
Library (PAL)
R Integration for
SAP HANA
R
Data Pre-Processing and Loading
SAP Data Services, Information Composer, SLT, DXC, Hadoop
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
22
Association Analysis
Apriori
Apriori Lite
Time Series Analysis
Single Exponential Smoothing
Double Exponential Smoothing
Triple Exponential Smoothing
Cluster Analysis
K-Means
Kohonen Self Organized Maps
Outlier Detection
InterQuartile Range Test (Tukey’s Test)
Variance Test
Anomaly Detection
Classification Analysis
C4.5 Decision Tree Analysis
CHAID Decision Tree Analysis
K Nearest Neighbour
Multiple Linear Regression
Polynomial Regression
Exponential Regression
Bi-Variate Geometric Regression
Bi-Variate Logarithmic Regression
Logistic Regression
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
Data Preparation
Sampling
Binning
Scaling
Other
ABC Classification
Weighted Scores Table
23
R is a software environment for statistical computing and graphics
Open Source statistical programming language
Over 3,500 add-on packages; ability to write your own functions
Widely used for a variety of statistical methods
More algorithms and packages than SAS + SPSS + Statistica
Who’s using it?
Growing number of data analysts in industry, government, consulting, and academia
Cross-industry use: high-tech, retail, manufacturing, CPG, financial services , banking, telecom, etc.
Why do they use it?
Free, comprehensive, and many learn it at college/university
Offers rich library of statistical and graphical packages
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
24
A leader in predictive
“SAP is a newcomer to big data predictive analytics but is a Leader due to a strong architecture and strategy .”
Comprehensive and holistic approach to “Big Data”
“SAP also differentiates by putting its
SAP HANA in-memory appliance at the center of its offering, including an indatabase predictive analytics library
(PAL), and offering a modeling tool that looks a lot like SAS Enterprise Miner and
IBM SPSS Modeler.”
The Forrester Wave™ is copyrighted by Forrester Research, Inc. Forrester and Forrester Wave™ are trademarks of Forrester Research, Inc. The Forrester Wave™ is a graphical representation of Forrester's call on a market and is plotted using a detailed spreadsheet with exposed scores, weightings, and comments. Forrester does not endorse any vendor, product, or service depicted in the Forrester Wave. Information is based on best available resources. Opinions reflect judgment at the time and are subject to change .”
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
25
• Introduction to Predictive Analysis
• Use Cases, Demo & Customers
• Predictive Applications
• High Performance Applications (on SAP HANA)
• SAP Predictive Analysis
• Architecture and Algorithms
• Questions & Answers
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
26
Planning Assessment for Predictive
1 Analysis 2
Scope:
Assess goals for predictive Analysis and current state
Identify what data will be needed
Identify user groups and enablement plan
Roadmap to predictive Analysis maturity
Implementation of Predictive
Analysis Using HANA
Scope:
In addition to PA Quick Start, data integration with a HANA (or EDW) data source
Data model in HANA to support predictive model
Leverage HANA for faster performance
Duration: ~2 days
Resources
Decision Scientist
Duration: ~20 days
Resources
Decision Scientist
PA Tech Architect
Data Architect
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
27
1.
SAP macht Predictive Analysis!
2.
Mit SAP Predictive Analysis können Fachanwender ohne grossen Schulungsaufwand Data Mining betreiben.
3.
Mit SAP HANA geht es noch detaillierter und schneller.
4.
Business Applikationen bringen Predictive direkt in die Prozesse.
5.
Möglichkeit der gemeinsamen Entwicklung von kundenspezifischen Predictive Applikationen.
© 2013 SAP AG or an SAP affiliate company. All rights reserved.
28
Contact information:
Andreas Forster
Solution Advisor
SAP Schweiz
+41 797 01 8944, andreas.forster@sap.com
© 2013 SAP AG or an SAP affiliate company. All rights reserved.