New Text Analytics Add-on now available for Modeler Subscription.
Use case: Acquire and Retain Customers
- Predicting customer churn is difficult.
- Creating the right offers is challenging.
- Correlating staffing, products and other factors with customer acquisition is inefficient.
With IBM SPSS® Modeler, enterprises are delighting customers, building the right offers and aligning business needs while shrinking the time it takes to go from idea to experimentation, and then to production.
Read more case studies
Use case: Optimize logistics and prevent failures
- Error-prone, manual processes lead to equipment failures.
- Duplicate processes and operational waste are too common.
- Business continuity and security concerns are not being met.
Predicting potential maintenance issues or optimizing routes have never been easier with this visual drag-and-drop data science tool.
Use case: Build new offers and innovating business models
- Understanding how customers are reacting to and acting on information is difficult.
- Creating the right offers for the right channels is challenging.
- Spending too much time wrangling data and scripting the information flow inhibits efficiency and innovation.
From data preparation to applying machine learning algorithms, SPSS Modeler enables new ways of exploiting information. Now you can confidently create new offers, drive channel performance and optimize business processes for optimum team productivity.
Watch the video
Support for many data sources
SPSS Modeler can read data from flat files, spreadsheets, major relational databases, IBM Planning Analytics and Hadoop. You can extend the capabilities of SPSS Modeler to push back data processing with the SQL Optimization add-on (subscription) or the Analytic Server (perpetual license).
Visual analysis streams
SPSS modeler provides an intuitive graphical interface to help visualize each step in the data mining process as part of a stream. Now analysts and business users can easily add expertise and business knowledge to the process.
Automatic data preparation
SPSS Modeler automatically transforms data into the best format for the most accurate predictive modeling. It now only takes a few clicks for you to analyze data, identify fixes, screen out fields and derive new attributes.
SPSS Modeler can test multiple modeling methods, compare results and select which model to deploy in a single run. This enables you to quickly choose the best performing algorithm based on model performance.
A range of algorithmic methods
SPSS Modeler offers multiple machine learning techniques — including classification, segmentation and association algorithms including out-of-the-box algorithms that leverage Python and Spark. Users can now employ languages such as R and Python to extend modeling capabilities.
SPSS Modeler captures key concepts, themes, sentiments and trends by analyzing unstructured text data. Now you can uncover valuable insights in blog content, customer feedback, emails and social media comments.
Explore geographic data such as latitude and longitude, postal codes and addresses using SPSS Modeler. By combining that information with current and historical data you can generate better insights and improve predictive accuracy.
Support for open source technologies
SPSS Modeler enables the use of R, Python, Spark and Hadoop to amplify the power of analytics. You can also extend and complement these technologies for more advanced analytics while maintaining control.
Multiple deployment methods
Using SPSS Modeler Gold, data scientists can schedule jobs to run at the desired times. IT administrators can integrate deployment into existing systems for batch, real-time or streaming using IBM Streams. You can also deploy SPSS Modeler programs in the cloud using IBM Watson Machine Learning, a full-service IBM Bluemix® offering.
Machine learning methods and algorithms
SPSS Modeler supports decision trees, neural networks and regression models. Now you can take advantage of ARMA, ARIMA and exponential smoothing; transfer functions with predictors and outlier detection; benefit from ensemble and hierarchical models; support vector machine and temporal causal modeling; and employ time series and spatial AR for spatiotemporal prediction. Generative adversarial networks (GANs) and reinforcement also enable deep learning.
Try it now
Buy now and get started
Expert resources to help you succeed