Zoot was founded in 1990 and has been providing hosted decision management solutions since 1992. With a focus on financial services, Zoot’s clients include 3 of the top 5 U.S. banks and they work with clients of all sizes and across all lines of business.  Instant credit decisioning is one of their critical offerings, but about half of Zoot clients are leveraging their loan origination solution.

Zoot’s core solution stack is based on an ASP or SaaS infrastructure (though they have some on-premise deployments) using a tools and services approach to their applications, which allows them to expand into various solution areas.

SPOC® (Single Point of Contact) is the core service that works to process applications. SPOC performs stateless processing and is configured by Zoot’s WebRules® business rules developer tool. WebRules is a business logic editor that is designed specifically for business users and takes a unique approach by offering a GUI for the development of business processes. Processes can be defined that link rulesets, decision tables, decision trees, and scorecards as well as other processes. The overall environment is graphical, business friendly and fairly conversational.

ZUI™, another one of Zoot’s offerings, gives business users control to design and configure employee-facing, review screens and external facing application entry screens for kiosk, online, or mobile channels. This supports a Windows UI as well as web pages and the product set also offers support for batch processing and makes it easy to begin with objects derived from the data being manipulated in the system. It also integrates tightly with calls to WebRules for decision making.

These common tools and services support Zoot’s range of solutions:

• zLink Data Aggregation Solution
  Connections to dozens of data providers are pre-built so one connection to Zoot gives clients the ability to use multiple vendors. Clients can compare and contrast the results of using different providers or data types at different points in the decisioning process, testing new data providers and signing up with the vendors they prefer. The vendor network of providers is accessible across all of Zoot’s solutions. Supported data is available both as formatted data for presentation and unformatted data for execution from a single call to the data provider.
• zDecision® Consumer-Initiated Decisioning Solution
  Combines business rules, workflow, and data sources to make offers in realtime. Zoot commented that many of their clients have seen higher accept rates as a result of the instant response to product requests, something I have also noted.
• zAcquire® Instant Prescreen Decisioning Solution
  Similar to zDecision, this solution provides instant offers based on rules, workflow and data but is used to make unsolicited offers to consumers. zAcquire is used mostly to offer pre-approved, cross-sell products. Another use case is at check out in retail (to pre-approve credit). The solution offers failover between the bureaus and allows a lot of control for clients while managing the prescreen restrictions under FCRA.
• zOptimize® Multichannel Cross-sell Solution
  This solution includes multi-channel connections and an offer repository that tracks all product offers made across all channels. This allows a consumer to complete an application in one channel that was initiated in another. zOptimize also uses the decisioning engine combined with segmentation and predictive models to make more targeted offers to individual consumers.
• zOriginate® Loan Origination Solution
  Workflow, manual reviews, queues are included with the decisioning process to allow applications to move back and forth from manual to automated review. Applications are bounced to a manual queue for a specific reason and once that is addressed, the application flow back into automated processing through completion.
• zInitiate Account Opening Solution
  This solution provides a typical DDA opening foundation to make sure high risk accounts aren’t opened. Models and alternative data providers are integrated into the platform to predict close for cause and to optimize deposit and credit cross-sell offers for relationship-pricing and debit rewards.
• zEnvision® Credit Risk Lab
  Clients use actual, historical transactions in a nonproduction, simulation environment to see how results would change if credit policies, logic, and data sources were also changed. This solution provides a faster analysis of the impact of new credit risk policies, new attributes, and new models.

These solutions were built in response to specific client business problems Zoot has seen over their years in the industry. All of the solutions rely on their standard tools to provide direct control for the business – critical as IT is, they are the most constrained resource in their target companies. The solutions offer both a rapid time to market, while still allowing users to configure them easily as changes are required. Each solution has code promotion, champion/challenger, versioning, and highly integrated role-based access in support of business user control.

Zoot provides an infrastructure that is redundant (with 3 live processing centers) and high performing with capacity engineering to 10x their average load. This offers sub-second decisioning response times. Zoot is also PCI level 1 and SAS-70 Type 2/SSAE16 compliant and handles hundreds of millions of transactions per year.

Zoot believes their advantage is the flexibility of their solutions including the ability they give to client business users to tailor their solutions. Proven experience with large banks and a top to bottom focus on business user control are important to Zoot’s banking customers also. Finally Zoot is data independent, offering a high performance hosted environment and have a great deal of experience with systems integration. Their typical business customer has challenges with IT resources, making the need for hosted, easy to configure, business focused solutions very important. Eighty five percent of their business comes from the US but they do have an operating unit and data center in Europe also.

Zoot has some customers using their technology to build custom solutions and will be one of the vendors listed in the forthcoming report on Decision Management Systems platform technologies.

Working with our European partners (BCS), Decision Management Solutions has scheduled a series of three webinars at 7am Pacific/10am Eastern/16:00CET. Designed to be  live events that work for those in Europe, this is a foundation series on three core topics – Decision Management, Business Rules and Predictive Analytics. There is no restriction on attendance – Americans are welcome too – but they’re all a bit early  for those on the West Coast!

• An Introduction to Decision Management
  02/29/2012 7:00 AM US/Pacific
  Decision Management is a powerful approach for building a new class of information systems.
  Registration
• The use of Business Rules in Decision Management Systems
  03/14/2012 7:00 AM US/Pacific
  Business rules management systems are critical components in the effective development of Decision Management Systems.
  Registration
• The use of predictive analytics in Decision Management Systems
  04/11/2012 7:00am US/Pacific
  Data Mining and Predictive Analytics play a critical role in improving the effectiveness of Decision Management Systems.
  Registration

You can also register for the whole series here.

And for those of you who are based in or near Germany, why not come to the live workshop I am giving this June? Check out the details of my Decisions and Decision Management workshop in Berlin, June 4-5.

Oracle Advanced Analytics is a new Oracle database option (announced today) that bundles Oracle R Enterprise and Oracle Data Mining (reviewed previously). With this release, R becomes a first class native interface for the Oracle database along with SQL and the graphic interface that ships with Oracle Data Mining.  This allows analytic modeling code to be written in 100% R with the tables and views in the Oracle database appearing as R objects directly. There is no need for modelers to write SQL – they can just write R code and manipulate the data in the database. This makes it easier for R programmers to access the database (no extracting the data to a file, no writing SQL) and the availability of data extends to Oracle OLAP Cubes that can also be accessed from the R code.

Performance is good with the approach for a number of reasons. First, with this set up, the database computing hardware is used and all the R packages are being executed on the database server. The approach further improves performance by allowing the data to be accessed without extracting or moving it. Finally all the ODM algorithms are available to Oracle R Enterprise so that R packages can use the ODM algorithms already deeply embedded and optimized for the Oracle database as well as the Oracle Exadata and Oracle Exalytics machines.

Besides improving data access and performance for R, Oracle R Enterprise also allows a piece of R code that builds a model, makes a forecast or scores a customer to be treated as a database function. Once deployed to an Oracle database function this R code can then be called by any piece of SQL (in a BI tool like OBIEE or Java code or business rules). Any arbitrary R code can be executed in this way with no constraint on inputs or outputs or the code/packages being used. This supports the increasing focus of modelers on real-time scoring by making it easy to embed R code as SQL-friendly functions that can be called to calculate a score or make a prediction right when the decision is being made.

This release builds on previous work around making Big Data available to R. The Oracle R connector for Hadoop is available in conjunction with the support for R in the Oracle Big Data appliance. These allow you to run R against both Oracle’s own Big Data appliance and against a generic Hadoop/HDFS installation with no need to convert it to MapReduce for execution. This means that a user can develop a single R script that brings in data from an Oracle database, Oracle Big Data Appliance and HDFS and have it all look like R objects to the script. These scripts can then be deployed to the Oracle Database or Oracle Big Data infrastructure for real-time scoring against this diverse set of data sources.

This will clearly be a product considered in the forthcoming Decision Management Systems Platform Report.

Brooksource in Louisville, KY is searching for a Rules Management Developer for a Fortune 100 client in the healthcare industry. This position is within the Clinical Guidance group and they are seeking someone that has a development background and has experience working with the business side of the house.  This is a unique position that has a tremendous upside. The client is implementing the Blaze Advisor Business Rules Management system and is willing to train candidates with a development and business analyst type background on this tool.  They are looking for someone with around 2-5 years of .NET, C#, and SQL development that wants to be techno/functional.  This person will not solely be focused on development but rather touching most phases of the SDLC.  This is all new development so there will be minimal production support work.

The day to day will consist of ongoing analysis, design reviews, and testing/support.  There will also be interaction with the business partners to help them understand where in the process the development team is and what they are doing or planning on doing.  The goal with the implementation is to use Blaze to help understand what the policies and procedures are and then convert these from manual to automated processes.  They are seeking candidates with a go-getter attitude that are excited to learn and work with new tools to further their career. The position is in Louisville, KY and it’s a contract to hire, if that person is interested in going full-time. They are open to someone more junior willing to be trained.

Email Teddi at tnaegele@brooksource.com if interested.

Patrick over at Figurs sent out a newsletter that highlighted an article from 2010 Biggest Barriers to Business Analytics Adoption: People. The article highlighted the people and organizational issues in adopting business analytics and #1 was “Lack of understanding of how to use analytics to improve the business”. While it’s been a while since this was article was published, it was great to be reminded of the issue of business understanding as this remains a critical challenge to adopting analytics, especially more advanced analytics.

In fact this very problem is what has led me to develop a new workshop – Business Friendly Data Mining – that is running at Predictive Analytics World in San Francisco in a few weeks(register here and use code DMSBP12 to get 15% off the price of my workshop). This workshop focuses on decision discovery and on the effective modeling of repeatable decisions to build business/analytic/IT understanding and collaboration. It shows how this focus on decisions-first and an overall decision management framework helps you build the right models and increases the odds of a successful implementation by understanding how the models will need to be implemented. We have used this approach with a number of projects now and found that it fundamentally changes how the data mining team sees the problem and creates new opportunities for collaboration.

There’s also a nice white paper on why to be an early predictive analytic adopter on the Figurs site that you should check out and you might also enjoy our paper on Putting Predictive Analytics to Work. Don’t forget you can register for the workshop here or contact us info@decisionmanagementsolutions.com if you are interested in having an onsite version.

Jim Harris of the OCDQ Blog (Obsessive-Compulsive Data Quality) interviewed me for his OCDQ radio show recently and the podcast is now live – check it out on his blog. In the interview Jim and I discuss the whys and wherefores of Decision Management, the four principles of Decision Management Systems and the three legged stool among other things.

And you can win a copy of the book simply by entering Jim’s competition –  just Email Jim Harris by February 29, 2012 and tell him at least one of the four principles of decision management systems that I discussed. Enjoy!

I got a comment on one of my recent posts asking if I knew of any good free video resources on predictive analytics. While I have some videos up on the Decision Management Solutions YouTube Channel (youtube.com/user/DecisionManagement) I figured some of my readers must know of others. So, if you do, why not post a comment on this blog post with your suggestions.

The first webinar from my ongoing research into Decision Management Systems Platforms is coming up on February 16th at 10am PT – register here  for Four platform capabilities for Decision Management Systems.

This webinar kicks off what will be a continuing series of webinars as our definitive report on Decision Management Systems Technology Platforms comes to fruition in 2012. The report will describes the wide range of technology available – Business Rules Management Systems, Predictive Analytic Workbenches and Optimization Suites, as well as recent advances around in-database analytics.

Based on the initial version of the report, this webinar will describe the four key capabilities of a Decision Management Systems Platform and show how these components fit together into a coherent architecture.

Look forward to seeing you there.

Some time back I wrote a post called “It’s time to industrialize analytics“. In an ongoing twitter conversation (I am @jamet123) I referenced it and provoked some interesting responses that seem worth addressing in more than 140 characters. The conversation was between @JAdP, @deanabb, @merv, @ajbowles and myself and they are all worth following.

We spent some time discussing the analogy of furniture manufacturing as it applies to predictive analytic models. Too many models, I believe, are still produced using age-old (20+ years) hand crafted approaches with scripts, hand tuning, manual variable creation and much more. To make predictive analytics pervasive we need to industrialize this process and focus more on utility and less on craft. Finely crafted models are all well and good but the amount of economic value has to be considered. This is not to say that I believe all the art in models can or should be replaced with automation, only that this art and craft must be applied in a repeatable, manageable framework. Scripts become managed workflows, automation trawls through candidate variables, models are managed and monitored once deployed and so on.

One challenge raised with this approach is that ”cookbook” models can be misapplied. This is true but not I think a function of an industrial analytic process. Quite the reverse in fact as the use of a more industrial mindset allows for more models to be built more quickly. This allows, for instance, a model for each customer segment instead of one for the whole portfolio.

There was some discussion that if one industrializes or engineers processes & practices then at some point there will be accountability issues. Again I think the reverse is true. For many current models the only record of how the model was produced is the script on the modelers PC. There’s no documentation, no repeatability, no shared or shareable assets. I believe that a modeled, managed, industrial process for analytics is fundamentally more accountable not less.

It should also be noted that many of the tools that support a more industrial mindset are able to bring the art to bear effectively also, allowing you to decide if the last little improvement in model accuracy is worth it for each model.

Finally there was some discussion of the tools available out there. I review a lot here of these on the blog including tools aimed at non-modelers like SAS Enterprise Miner Rapid Predictive Modeler, IBM SPSS Modeler Advantage, KXEN and Predixion as well as tools aimed at providing broad automation and effective “industrial” support to modelers such as KNIME, Statsoft and FICO Model Builder. Plus of course there’s a whole range of deployment options to “industrialize” the process of getting these models deployed.

All this and more will be covered in the  forthcoming report on Decision Management Systems platform technologies.

StatSoft was founded in 1984 and started building statistical software when it first became practical to deliver on the PC. STATISTICA is an enterprise predictive analytics platform on the Windows platform with role-based access, connections to the various data sources that companies have and support for data exploration through to deployment. The product has four main pieces:

• Windows-based analytics Workbench for analysts.
• Decision Management to combine models and rules to automate decision-making.
• Enterprise Server to support multiple users in a client/server environment.
• Enterprise Workspaces to capture the data analysis process from end to end and for managing metadata, decision-making workflow etc.

STATISTICA is a long time Windows platform user and Microsoft partner. As a result it offers a solution that is tightly coupled with Intel multi-core chips very well integrated with Windows. Everything is available as an API call in .Net making it easy to integrate into SharePoint or other Windows applications.

The components get combined into various analytic applications such as a warranty analytics solution, credit scoring, collections, cross-sell, insurance fraud detection, subrogation, price optimization, marketing mix optimization and more. These solutions can be completely automated, accessing multiple data sources, running tens or hundreds of predictive analytic models, writing results back into the database and monitoring the performance of the models.

With version 11, StatSoft released the STATISTICA Decisioning Platform that pulls together all the existing product capabilities with new rules management, integrated rules scoring, and other capabilities. The suite now includes:

• Templated data access
• Data pre-processing
• Rules management
• Modeling tools including accelerated logistic regression
• Version control
• Direct deployment

Everything is managed in an enterprise metadata repository deployed on a relational database. Workflows and other components for model creation or business rules are created, managed in the enterprise repository and deployed to a server for execution. Multiple projects and folders can be managed in the repository and permissions are layered onto these. Data access templates, analysis templates, decisioning flows and rules are all managed in this repository. Decision flows with models and rules are checked in and then used to drive reporting (integration with MS document tools), batch scoring for writing back to the production database or deployment to the STATISTICA Live Score Server for real-time decisioning using web services calls. There is a Monitoring and Alerting server for dashboards that monitor model performance and there is an integrated Document Management System for version control and approvals of models.

A decisioning flow involves several steps using the STATISTICA Enterprise Manager product. At each stage elements are retrieved from the repository based on the access defined for users and can be written back to the repository for management and reuse.

1. The first step is to retrieve data from data connection and configuration templates. Users may have access to the underlying queries or just to the data. Data from multiple data connections can be used and a wide range of ETL functions are available in the data manipulation step.
2. Data can be prepared and recoded, using Weight of Evidence for instance, and these transformations are then deployed as rules that can be versioned and reused. The rules are sequential and can assign text labels as well as transform the data. The rules are deployed to the enterprise server and can be associated with the data source. They can then be included in the defined workflow.
3. Models can then be built using various modeling techniques and embedded in the flow. A wide range of modeling techniques are supported and the workflow can create multiple models, combine or compare them etc.
4. Additional rules can be added to the workflow. The rules node contains a sequential set of rules built using an editor that has some integration with the data structures being manipulated and has a nice tree structure to allow rules to be collapsed. Temporary variables can be managed and models can be executed by the rules as necessary. Reason codes can be assigned using array handling that lets you build a set of reason codes. Rules can be reused across batch and real-time environment and multiple workflows. Rules have access to the full range of mathematical functions also.
5. The whole workflow can then be deployed to the various deployment options.

A debugger allows a set of records to run through the flow and see which transactions fired which rules. While the rules do not offer conflict detection there is some error detection (use of a variable that is not defined for instance) and some tools in the enterprise platform to see which objects refer to which other objects. Users can run multiple paths in a workflow for comparison purposes and can then use analysis tools built into the modeling environment to see what difference a change would make or which approach would be more profitable.

Besides executing the complete decisioning workflows using the STATISTICA products, all of the models can also be deployed as C, C++, PMML, Visual Basic, SAS, Java or C# Stored Procedure. The tool also supports Visual Basic scripting and this can also be used to push things into the database programmatically.

Statsoft will be one of the vendors listed in the forthcoming report on Decision Management Systems platform technologies.