developerWorks is a free web-based professional network and technical resource center from IBM for software developers, IT professionals, and students worldwide.

List of developerWorks Articles about IBM SPSS Software: List

IBM Business Analytics Proven Practices: A Framework For Text Classification Using IBM SPSS Modeler

This article explores building SVM-based classification framework for text classification.
IBM Business Analytics Proven Practices: IBM SPSS Modeler – ODBC Configuration Best Practices and Troubleshooting

An overview of Open Database Connectivity (ODBC) configuration, best practices when performing these tasks, and troubleshooting techniques to assist in the resolution of common problems in this area.
Explore the advanced analytics platform, Part 6: Dive into orchestration with a combination of SPSS, Operational Decision Management (ODM), and Streams using care and fraud management case studies

An essential component of any analytics platform is the ability to analyze large volumes of data at high velocity that results in real-time actionable steps. Often, intelligent processes require attention and focus on a few “out of range” observations midst a much larger field of “normal” observations. The real-time action requires selecting, focusing, and investigating these observations while dealing with data-in-motion. At the same time, we must understand historical trends and adapt to the changing definition of “out of range”. This article describes the D4 (Discover, Detect, Decide, Drive) pattern, which permits high-speed analytics with rapid execution while under extreme data velocity and volume requirements. We then introduce two example use cases, identify architecture components, and discuss some integration design considerations common with the D4 pattern.
IBM Business Analytics Proven Practices: SPSS Modeler Premium Entity Analytics Technical Q&A

This document addresses some of the frequently asked questions regarding IBM SPSS Modeler Premium Entity Analytics (EA) ranging from what is EA through technical details on how to use the product.
IBM Business Analytics Proven Practices: SPSS Collaboration and Deployment Services – Top 5 Uses

The IBM SPSS Collaboration and Deployment Services product (a.k.a. C&DS) is a JEE based application that can be leveraged by other IBM SPSS products (Modeler, Statistics, Analytical Decision Management, etc.) to provide additional capabilities. This article will describe five ways that C&DS can be used to enhance your IBM predictive analytic solution.
Customer segmentation analytics with IBM SPSS

Learn how to segment customers by using IBM SPSS, IBM PureData System for Analytics powered by Netezza, and IBM DB2 for Linux, UNIX, and Windows. Merge data from disparate data sources, create a predictive model, and use it to segment customers taking into consideration multiple dimensions, such as age, income, education, etc.
Survey text mining with IBM SPSS Text Analytics for Surveys, Part 2: Configuring domain-specific linguistic resources

This two-part series of articles demonstrates text mining with IBM SPSS Text Analytics for Surveys, version 4.0.1. Part 1 of the series presents sample survey data about touchscreen devices and presents an analysis of the data that uses built-in linguistic resources of SPSS Text Analytics for Surveys. Part 2 starts from the conclusions that are drawn in Part 1. It explores more features of SPSS Text Analytics for Surveys with special focus on how to configure user-defined resources to examine domain-specific terminology. It describes the process of categorizing responses that are based on user-defined rules.
Also available in: Russian
Create new nodes for IBM SPSS Modeler 16 using R

IBM SPSS Modeler, a powerful analytic tool, supports all phases of a data mining process, including data preparation, model building, deployment, and model maintenance. The IBM SPSS Modeler UI makes use of a visual data mining workbench that provides built-in data preparation, modeling, and output nodes that enable rapid development of the analytic assets.
IBM Business Analytics Proven Practices: Entity Analytics Performance Guide for DB2

DB2 tuning guidance around SPSS Modeler Premium Entity Analytics.
Survey text mining with IBM SPSS Text Analytics for Surveys, Part 1: Exploring sample survey data

This two-part series of articles steps through the process of text mining by using IBM SPSS Text Analytics for Surveys, version 4.0.1. Part 1 describes the objectives of survey text mining and presents sample data of a survey for analysis. In a tour of survey analytics, explore the capabilities of SPSS Text Analytics for Surveys in a step-by-step manner. Every step shows you a bit of information about your sample data. Learn how to use SPSS Text Analytics for Surveys to completely decipher survey data.
Also available in: Russian
Use SPSS Statistics direct marketing analysis to gain insight

Learn how to use the RFM analysis process of the Direct Marketing module of IBM SPSS Statistics. Using this process, nontechnical users can analyze their customer data.
Also available in: Chinese   Russian   Spanish
Recognize physical activity on mobile phones with IBM Worklight and IBM SPSS Modeler

Recognize mobile activity with a service developed with IBM Worklight and IBM SPSS Modeler in this high-level overview. See how to detect and track the physical activity of mobile phone users. The authors share techniques to clean training data, select features, choose the best classification algorithm, and validate the model.
Also available in: Russian
IBM Business Analytics Proven Practices: Introduction to Python Scripting in IBM SPSS Modeler

This document provides an introduction to Python scripting in IBM SPSS Modeler.
Also available in: Russian
IBM Business Analytics Proven Practices: Bulk Loading Via External Loader From IBM SPSS Modeler: Configuration Best Practices and Troubleshooting

Best practice advice for system and database administrators when configuring the bulk loading via external loader functionality of IBM SPSS Modeler.
Also available in: Russian
Mine spatial data with space-time-boxes in IBM SPSS Modeler and visualize the data with R

Combine traditional data, unstructured data, and spatial data from many different types of data sources and use space-time-boxes to mine the data for insight. Add R visualization to make it easier to build accurate, predictive models quickly and intuitively, without programming.
Also available in: Russian
Explore the advanced analytics platform, Part 4: Analyze location data to determine movement patterns using a mobility profile pattern

You can create several analytics patterns by using the Advance Analytics Platform. This article describes how to create the mobility profile pattern by analyzing location data, which is captured across time and space for an entity, to determine movement patterns. Such information can be valuable for various actions such as sending timely marketing campaigns based on locally appropriate offers or predicting future flow of traffic. A use case that involves location data from mobile devices illustrates the concepts. Also, learn about the underlying tools that are required to create the patterns.
Also available in: Chinese   Russian
Improve your agile development lifecycle with SPSS

Learn how to build a lean analytics strategy by using IBM SPSS. Your project managers can optimize the development lifecycle, focusing attention where it needs to be. Doing so gives product teams the opportunity to make real-time decisions about feature implementation, and most importantly, management can make quick decisions on resource allocation.
Also available in: Russian
IBM Business Analytics Proven Practices: Revival Procedure for Predictive Maintenance and Quality Solution

A description of the steps to revive the IBM Predictive Maintenance and Quality Solution environment after an outage.
Also available in: Russian
Predict prospect-to-customer conversion with analysis of surveys and SPSS Statistics

Surveys of customers and prospects are becoming more common as web-based tools allow for quick deployment. As this information floods into the enterprise, it is often not organized or merged with other survey efforts. Most marketing and sales departments glance at the results, cherry-pick those customers who bother to write comments, and then ignore the rest. IBM SPSS Statistics comes from a background of survey analysis, but most business managers and analysts do not have that background. Those people can use the Direct Marketing menu of SPSS Statistics to develop a predictive model for prospects who are more likely to purchase products. In this article, explore the best practices to create a statistically valid sample, how the predictive algorithm in SPSS Statistics works, and how to apply the predictive model to ongoing surveys.
Also available in: Russian
Apply SPSS analytics technology to big data

Learn about the new capabilities in SPSS for working with big data. SPSS analytic assets can now be easily modified to connect to different big data sources and can run in different deployment modes (batch or real time). Components of the SPSS platform now work with IBM Netezza, InfoSphere BigInsights, and InfoSphere Streams to enable analysts to use powerful analytics tools with big data.
Also available in: Chinese   Portuguese   Spanish
Explore the advanced analytics platform, Part 3: Analyze unstructured text using patterns

In this article you will learn how to use design patterns to analyze unstructured text in the context of big data. As multiple tasks are usually required to solve business challenges in this space, the authors describe simple design patterns used to architect solutions that use data in unstructured text documents.
Also available in: Chinese   Russian
Calling R from SPSS

Starting with version 16, IBM SPSS provides a free plug-in that enables you to run R syntax from within SPSS. The plug-in connects R to the active database. You can write results that are obtained from R into a new SPSS database for further manipulation in SPSS. This article is for the reader who is familiar with R and SPSS but who has not yet tried to use them in tandem.
Also available in: Russian
Do I need to learn R?

R is a flexible programming language designed to facilitate exploratory data analysis, classical statistical tests, and high-level graphics. With its rich and ever-expanding library of packages, R is on the leading edge of development in statistics, data analytics, and data mining. R has proven itself a useful tool within the growing field of big data and has been integrated into several commercial packages, such as IBM SPSS and InfoSphere, as well as Mathematica. This article offers a statistician’s perspective on the value of R.
Also available in: Chinese   Russian
Comment lines: Making good decisions through business analytics

In order to make good decisions, you need to understand what’s going on around you. But it can take a lot of work to make sense of the vast and diverse data that is available to you, and even more work to understand how it can help you to make decisions. Fortunately, IBM has done a lot of this work for you. Top-tier statistical and optimization packages like IBM SPSS and IBM ILOG CPLEX show IBM’s continuing commitment to business analytics technology solutions that help you use and understand the data that supports your business. With unique levels of accessibility to this data within reach, the next important task for IT services everywhere is putting this data to good use.
Also available in: Chinese   Russian
IBM Business Analytics Proven Practices: SPSS Modeler Entity Analytics Performance Guide

Tuning guidance around SPSS Modeler Premium Entity Analytics.
Also available in: Portuguese   Spanish
IBM SPSS Collaboration and Deployment Services 5.0: Clustering

The IBM SPSS Collaboration and Deployment Services 5.0 product (also known as C&DS 5.0) is a JEE-based application that can be leveraged by other IBM SPSS products to provide enhanced capabilities. As a JEE-based application C&DS requires an application server to run on, and the logical choice is the IBM WebSphere Application Server. This article describes how you can configure C&DS 5.0 to run on an IBM WebSphere Application Server Cluster in order to provide high availability and scalability.
IBM Business Analytics Proven Practices: Using Database Questions In Survey Wizards

Introducing the concept of using database questions in conjunction with survey wizards.
Target customers through the Direct Marketing menu of SPSS Statistics

Discover how to use the simple but effective customer-targeting algorithms in the SPSS Statistics Direct Marketing menu. Learn about the statistical issues, the commonly used customer characteristics, and potential danger points. Review how to transition from SPSS Statistics Direct Marketing models to big data.
Also available in: Russian   Spanish
Retention modeling for technology service contracts

Explore tips and tricks for building a model that predicts which customers are most likely not to renew their technology service contracts. Review the critical steps, regardless of the particular statistical method, and important considerations about implementation strategies of the model.
Regression analysis of construction data with IBM SPSS Modeler

This is the second article of a sequence that shows how IBM SPSS Modeler can meet the needs of different industries. Read about pattern recognition, machine learning concepts, and how SPSS Modeler supports civil construction activities.
Create customer segmentation models in SPSS Statistics from spreadsheets

Learn how to bring a spreadsheet of raw data into SPSS Statistics and apply two classification algorithms to create customer segmentation models. Then, use options in SPSS Statistics to create persistent files that contain the rules for the models that can be used for both deployment of customer classifications back to spreadsheets and into a big data environment.
Also available in: Russian   Spanish
B2B customer segmentation

Learn the process of developing a business-to-business customer segmentation, including the challenges of segmenting business customers and important differences from more common consumer segmentations. Consider methodologies and suggestions on how to work closely with business users on implementation.
Also available in: Spanish
Statistical analysis of medical data with IBM SPSS Modeler

IBM SPSS provides the main algorithms to recognize patterns that are identified in scientific literature about statistical data analysis, such as artificial neural networks, supporting vector machines, decision trees, and clustering algorithms. This article presents an application of SPSS Modeler software, as a medical diagnosis support system, helping identify both benign and malign tumors.
Also available in: Spanish
Build social media datamarts using SPSS text mining tools

The rise of social media has changed the way big brands do business. Customers are online, conversing, asking advice, performing comparisons, and influencing others. These individual-level behaviors embedded in raw social media data represent consumer preference, purchase history, significant life events, mood, personality, and other attributes that can be derived through text mining and stored in a social media datamart.
Also available in: Chinese   Vietnamese   Portuguese   Spanish
Optimal segmentation approach and application

Learn about clustering, classification, and segmentation techniques that are specific to the development of targeted marketing, product development, and profiling solutions. Explore popular segmentation approaches and algorithms and their strengths and limitations.
Also available in: Chinese   Russian   Portuguese   Spanish
Integrate customer segmentation predictive analytics into business applications

Customer segmentation is an excellent first step for technical people entering into predictive analytics. Yet, integrating the statistical results into business processes can be difficult. This article provides guidance and a progressive procedure for deploying a segmentation model to business users.
Also available in: Russian   Portuguese   Spanish
Where to start data mining in wholesale distribution

Large distributors are blazing the way in predictive analytics for distribution, which puts mid-sized distributors in a great position to take advantage of the larger companies’ successes and failures. In this article, discover examples of how predictive analytics can be used to improve business operations in several different function departments in a wholesale distributor, and learn about the IBM product set, which works from exploration and first applications to big data as your skills and data grow in the future.
Also available in: Chinese   Russian   Portuguese   Spanish
Predicting the future, Part 4: Put a predictive solution to work

This final article of a four-part series focusing on the important aspects of predictive analytics focuses on the deployment of predictive analytics, or the process of putting predictive solutions to work.
Also available in: Chinese   Russian   Portuguese   Spanish
Predicting the future, Part 3: Create a predictive solution

Put the techniques covered in Part 2 to use by learning how to create a predictive solution.
Also available in: Chinese   Russian   Portuguese   Spanish
Microsegmentation solutions for healthcare insurers

Learn more about technological changes in the healthcare industry, including a member-focused shift toward customization of health offerings to drive increased member satisfaction and retention. Explore two segmentation-based case studies using SPSS Statistics Base and decision trees.
Also available in: Portuguese
Predicting the future, Part 2: Predictive modeling techniques

This second article of a four part series focuses on predictive modeling techniques and the mathematical algorithms that make up the core of predictive analytics.
Also available in: Chinese   Russian   Vietnamese   Portuguese   Spanish
Predicting the future, Part 1: What is predictive analytics?

Predictive analytics helps you discover patterns in the past that can signal what is ahead. Gain an understanding of data-driven analytics versus business rules and expert knowledge and learn how both can enhance your decision-making ability.
Also available in: Chinese   Russian   Vietnamese   Portuguese   Spanish
Integrating SPSS predictive analytics into Business Intelligent applications, Part 2: Integrating the scoring service into an ILOG JRule

In Part 2 of this series, you’ll learn how to use an SPSS predictive scoring service as an additional factor when quoting a premium for an insurance policy. In the scenario, predictive analytics are used to streamline the process of customer acquisition, by predicting the future risk behavior of a customer, thus leading to informed pricing decisions that mitigate future risk. Using the insurance quotation scenario from Part 1, you’ll learn how to use an SPSS scoring service and ILOG JRules, to create and deploy business rules that have a predictive dynamic factor.
Integrating SPSS Model Scoring in InfoSphere Streams, Part 1: Calling Solution Publisher from an InfoSphere Streams operator

This tutorial describes how to write and use an InfoSphere Streams operator to execute an IBM SPSS Modeler predictive model in an InfoSphere Streams application using the IBM SPSS Modeler Solution Publisher Runtime Library API.
Also available in: Chinese
Integrating SPSS Model Scoring in InfoSphere Streams, Part 2: Using a generic operator

Part 1 of this series describes how to write and use an InfoSphere Streams operator to execute an IBM SPSS Modeler predictive model in an InfoSphere Streams application using the IBM SPSS Modeler Solution Publisher Runtime library API. Part 2 takes the non-generic operator produced in Part 1 and extends it to be a generic operator capable of being used with any SPSS Modeler stream without any custom C++ coding needed.
Also available in: Chinese
Integrating SPSS predictive analytics into Business Intelligent applications, Part 1: Integrating SPSS Modeler and Collaboration and Deployment Services

In this article, you’ll learn how you can use IBM SPSS predictive analytics to make better decisions using a sample insurance quotation scenario. Using SPSS Modeler and SPSS Collaboration and Deployment Services, you’ll learn how to integrate an SPSS scoring service and automated model refreshing into an existing enterprise environment.
Modeling trains with SPSS

The ability to predict a failure before it happens is tremendously valuable. Learn how an IBM team worked with a train manufacturer to develop this capability using IBM SPSS Modeler and IBM DB2. In this instance, the team used SPSS to identify patterns in data and DB2 to handle moderately complex mathematical calculations directly within SQL.
Also available in: Chinese
Predictive analytics on SAP with SPSS and InfoSphere Warehouse

Predictive analytics software helps you to find non-obvious, hidden patterns in large data sets. Current tools for predictive analytics, such as SPSS (an IBM company) and IBM InfoSphere Warehouse, expect data to be represented in an appropriate way before the actual analysis can take place. However, you may have cases where the data you want to analyze is not readily available in a format these tools can recognize. For example, SAP systems are widely used by many companies across a variety of industries, but data in SAP systems is not directly accessible to these tools. This article shows you how to use IBM InfoSphere Information Server to extract data from SAP systems for analysis within InfoSphere Warehouse and SPSS PASW Modeler.
Also available in: Chinese   Portuguese