Technology: Statistics, Data Mining, Predictive Analytics Breakout Sessions
These sessions examine the latest product and solutions released from SPSS, and offer a preview of the technology currently under development, and learn how organization are using SPSS solutions to solve business problems.
Speakers and session(s) subject to change.
Some sessions might apply to more than one track.
Click here for the complete agenda
Enhancing the quality of non-stable production processes
Hans Dörmann-Osuna
Project Manager Quality/Production
BMW Group
Germany
How can data mining help solve engineering problems? In the manufacturing of an alloy metal, non-stable processes are not controllable with standard statistical process control (SPC) tools. Therefore, each produced part has to be checked. Results from quality checks, however, can be used to improve process settings. The BMW Group’s Landshut plant used SPSS technology to combine captured production data and known quality results in order to develop a model that predicts the quality of parts and process. This model provides BMW with better knowledge of the influence of process parameters and the quality of parts. The result? Faster development time and the implementation of new products in current production processes.
In this presentation, BMW will discuss how it uses data mining with production data to lower reaction time and enhance the quality of production processes.
Breakout Session 6: Tuesday, 15 May 2007
GGRAPH and Python
Raynald Levesque
Vice President
Aon Consulting, Inc.
Canada
If you’ve heard of www.spsstools.net or of the book, SPSS Programming and Data Management, you’ve heard of Raynald (Ray) Levesque. Ray has been an enthusiastic user of SPSS software since 1992.
During this session, Ray will provide examples of the joint use of Python and GGRAPH. Since GGRAPHs cannot conveniently be used within macros, Python is the best option whenever GGRAPHs need to be generated for various sets of variables or with parameterised options. Ray will also present:
- Good sources of information (Web sites and books) on Python
- Python tips for SPSS users
- Various data management utilities he recently wrote in Python
- His custom-made SPSS toolbar, complete with related *.bmp, syntax, and scripts, as well as detailed instructions to install it on your Windows XP platform
Downloads:
Examples
Python
examples.sps
Example to export to Excel.sps
Export from
spo.xls
My toolbar
Scripts.sbs
Show MX errors.sbs
Apply Autofit.sbs
Find Expression
in Log.sbs
Replace left pane page title.sbs
Find error in log.sbs
Search label in output.sbs
Syntax.sbs
Get Employee data.sbs
Clear transformations.sbs
Dataset close all.sbs
Enddefine.sbs
Python files
Change Sgt Template on the fly.py
Compare two files.py
Delete variables.py
Display Labels.py
Find empty variables.py
Graph size.py
Load all files meeting pattern.py
Scatter
plot matrix with correlations.py
Standardize variables.py
Breakout Session 7: Tuesday, 15 May 2007
SPSS Inc.’s Long Term Product Vision
Jason Verlen
Vice President, Marketing
SPSS Inc.
USA
Have you ever wondered how SPSS’ technology strategies will affect your
organisation now and in the future? If so, your questions are about to
be answered. This session offers a unique opportunity to hear about SPSS’
technology vision. We’ll address a variety of questions you may have,
including:
- What is SPSS’ high-level product strategy?
- Is SPSS a tools or an applications company?
- Going forward, and considering SPSS’ broader product vision, will I still be able to use the tools that I depend on today?
- How do other SPSS tools and technologies work with the ones I already use?
- How can I implement them in my organisation?
- How can SPSS technologies help me deploy my work to other types of users in my organisation?
- What are some key capabilities that SPSS will soon release, and how will they benefit my organisation?
Breakout Session 1: Monday, 14 May 2007
The Predictive Enterprise: From Vision to ROI
Colin Shearer
Senior Vice President, Market Strategy
Erick Brethenoux
Vice President, Corporate Development
SPSS Inc.
USA
In today’s world, a unique combination of trends and factors is driving
the uptake of predictive analytics in organisations across all sectors.
The explosion of data volumes and the availability of advanced analytical
technology coincide with an unprecedented focus on generating higher
return on investment (ROI) in business systems and processes.
SPSS’ vision is to enable organisations to evolve into Predictive Enterprises,
getting maximum value from their data assets and leveraging the results
of analysis to deliver tangible benefits and boost ROI across their operations
and throughout their business processes. Attend this session to hear
how SPSS partners with clients to dramatically improve business processes
leading to customer intimacy (e.g., CRM), operational excellence (e.g.,
risk management), and product leadership (e.g., concept testing) through
uniquely harnessing customer data, integrating predictive analytics technologies,
and efficiently deploying decisions across mission-critical processes.
Breakout Session 2: Monday, 14 May 2007
What’s New in SPSS 16.0?
Kyle Weeks, Ph.D.
Director, Product Management
SPSS Inc.
USA
SPSS 16.0 continues our rich tradition of regularly adding significant, new features to our flagship software. As a current SPSS user, you’ll want to attend this session and learn what’s new.
SPSS 16.0 offers:
- A new Java interface to SPSS allowing for Windows, Mac, and Linux versions of SPSS, a searchable Output Viewer, resizable dialogs and more
- More powerful statistics, including a new Neural Networks add-on module, a new Partial Least Squares algorithm, a new Cox Regression for Complex Samples module, support for algorithms written in R and improvements to Generalized Linear Models and General Estimating Equations
- More powerful data management with features such as Unicode support, import/export of Excel 2007 data, and an improved Data Editor
- Improved programmability, which provides the ability to extend the SPSS product with the full capabilities of the Python programming language
- Support for the Predictive Enterprise both with multithreaded algorithms and with the SPSS Adapter for SPSS Predictive Enterprise Services, which provides a centralized, secure, auditable repository for your analytical assets and processes
Breakout Session 3: Monday, 14 May 2007
Introduction to Clementine
Tom Khabaza
Director, Product Marketing
SPSS Inc.
United Kingdom
Join us for this session to learn all about Clementine, SPSS’ leading data mining workbench. You’ll hear how Clementine delivers maximum productivity for analysts by offering a comprehensive range of capabilities, which are integrated through a visual workflow interface and support the entire data mining process. We will cover:
- What is Data Mining and how does it fit with Predictive Analytics?
- An overview of the Clementine data mining workbench and how it is used
- The range of data mining operations supported by Clementine
- The range of options that can offer additional benefits with Clementine
- How Clementine can be both a desktop tool and the core of a Predictive Enterprise
Breakout Session 4: Monday, 14 May 2007
How Can Data Mining Help Improve my Business?
Tom Khabaza
Director, Product Marketing
SPSS Inc.
United Kingdom
You’ve probably heard of data mining but may wonder what it’s all about. There’s been a lot of coverage in the press, but is it all accurate? In this presentation we’ll explain in simple terms what data mining is, and the wide range of ways it can improve a business. These include enhancing customer processes, making it easier to get new customers, sell to existing customers and keep them longer, detect fraud or crime, reduce and manage risk, improve quality, and make your business smarter in many ways. We’ll focus on how and why data mining can improve a business, and also give you practical guidelines on how to get started and achieve success quickly.
Breakout Session 3 : Monday, 14 May 2007
Introduction to SPSS Text Analysis for Surveys
Stuart Torzewski
Senior Product Manager
SPSS Inc.
USA
This session is intended for users of SPSS for Windows who ask open-ended survey questions but do not use SPSS Text Analysis for Surveys to categorize or “code” the text responses. It is also suitable for Dimensions users interested in automating the coding of survey text responses.
We will review the objectives of asking open-ended questions and the challenges of categorizing text responses. Then we’ll describe the product’s features and benefits and explain how it complements other SPSS products. The majority of time will be spent demonstrating how easy it is to import text responses, extract and classify concepts, refine extraction results, create categories and categorize responses, export quantitative results, and analyze and graph the results using SPSS for Windows.
Breakout Session 4: Monday, 14 May 2007
Best Practices: Inbound and Outbound Marketing
Chet Friedman
Director, Product Marketing
SPSS Inc.
USA
The marketing profession has experienced a renaissance in recent years due to the powerful capabilities of predictive analytics. These techniques have enabled forward-thinking marketers to evaluate customer segments for profitability and lifecycle management, create more targeted outbound marketing campaigns, and optimise messaging across a number of competing metrics, during both outbound campaigns and inbound customer interactions. Predictive analytics can be applied in real time across channels, so that e-mail, call centre, Web, and in-person interactions can all be optimised.
Attend this presentation to learn how new marketing capabilities have helped other companies attract and keep customers and increase profits—and see where marketing is going next.
Breakout Session 6: Tuesday, 15 May 2007
What’s New in Clementine 11.0?
John Held
Product Manager
SPSS Inc.
USA
As a current Clementine user, you’ll want to attend this presentation to learn about the upcoming Clementine 11.0 release. We’ll discuss the new features and capabilities in this release, and review how Clementine 11.0 will help your organization make more informed decisions and maximize your returns.
New features planned for Clementine 11.0 include:
- Significant improvements in scalability and server performance
- Enhancements that make it far easier to implement complex data transformations
- Automated parallelized training of multiple models and best model visualization
- New machine-learning and statistical algorithms
- A new presentation-ready graphics engine
- Tighter integration with SPSS for Windows
- New deployment options and extended PMML support
- Privacy and security enhancements
Breakout Session 5: Tuesday, 15 May 2007
Introduction to Programmability in SPSS
Jon Peck
Principal Software Engineer
SPSS Inc.
USA
The SPSS Programmability Extension provides the ability to extend the SPSS command syntax language with the full capabilities of external programming languages. New features added to the SPSS Programmability Extension in SPSS 15.0 enable you to create first-class user-defined procedures, provide an interface for user procedures, and send results from these procedures into an SPSS pivot table in the Output Viewer.
In this session, we will demonstrate how to use Python® (a free object-oriented programming language), the SPSS Output Management System (OMS), and the new variable attributes feature within SPSS. We will show how you can manage a variety of tasks with the SPSS Programmability Extension, including how to:
- Create statistical procedures
- Create dialog boxes
- Control job flow based on statistical output
- Create transformed variables that retain their formulas and can be updated when new data is received
Breakout Session 4: Monday, 14 May 2007
What’s New in Text Mining for Clementine 5.0?
Stuart Torzewski
Senior Product Manager
SPSS Inc.
USA
Eric Martin
Product Marketing Manager
SPSS Inc.
France
This session is intended for users of earlier versions of Text Mining for Clementine. It is also suitable for Clementine users interested in becoming involved with text mining. You will see a demonstration of this new version’s major advancements and new features, including:
- Analyzing RSS feeds (such as blogs or news feeds) using the new Web Feed node
- Using new classification and clustering algorithms to aggregate a huge number of concepts under a small number of categories
- Interactively exploring and displaying text data and patterns using new graphs that enable instant, on-the-fly analysis
You will also learn how extracted concepts and categories can be combined with existing structured data and applied to modeling using Clementine’s full suite of data mining tools to yield better and more focused decisions.
Breakout Session 7: Tuesday, 15 May 2007
Managing the Predictive Enterprise Today and Tomorrow
Malcolm Lightbody
Product Manager
SPSS Inc.
United Kingdom
SPSS Predictive Enterprise Services is the backbone of the Predictive Enterprise. This application enables organizations to centralise and securely manage in an auditable manner:
- Analytical assets, including Clementine streams, SPSS syntax, and SAS code
- Predictive analytics processes, including model evaluations, analytical reports, and high-volume model scoring
SPSS Predictive Enterprise Services now offers enhanced capabilities for model lifecycle management and model self-learning, and additional integration with SPSS products.
Attend this session to learn about the features in current and upcoming releases of SPSS Predictive Enterprise Services.´
Breakout Session 8: Tuesday, 15 May 2007
Text Analytics Trend: Toward a Multi, Multi, Multi World!
Olivier Jouve
Vice President, Market Strategy
SPSS Inc.
France
More than 80 percent of an organisation's data is contained in free-text form, also known as unstructured data. This presentation describes how organizations use text analytics to analyze unstructured data—and dramatically enhance a variety of applications. It also highlights the future of the text analytics market, including a discussion of multi-source, multilingual, and multi-vertical approaches.
SPSS text analytics, based on natural language processing technologies, helps you leverage the value of unstructured data by extracting concepts, events, and sentiments. As a result, you gain greater insight from articles, reports, surveys, call centre notes, e-mail, Web chats, blogs, and other types of text documents.
By combining unstructured and structured data and integrating it into the SPSS Predictive Analytics framework, SPSS enables you to gain a 360-degree view of your customers.
Breakout Session 5: Tuesday, 15 May 2007
