Predictive Analytics Made Easy

While we can’t say “long gone are the glory days of the statistician, data scientist, and analyst” – the development of IBM SPSS’ Analytic Answers is a great first step into Predictive Analytics for specific organizations that are interested, but don’t know where to start. This communique will outline some very basic principles about what Analytic Answers IS and what it is NOT. As mentioned in previous posts, Analytic Answers seeks to answer very specific questions for very specific market segments, utilizing very specific columns or variables in a data set.

First, let’s talk a little bit about the structure: Analytic Answers is a cloud based (SaaS) solution hosted by IBM. Lodestar and IBM will work with you to identify very specific parts of your data that are required in order to get your questions answered. Lodestar will work with you to prepare your historical data, which will be sent to IBM so they can build your model. About 2 weeks later, you should be able to log into a web page and run new data (a CSV file) against the model to get your results. What you receive back is your CSV file with some additional variables at the end: The prediction, the confidence score (how sure we are about the prediction), and a Prescribed Action. To be clear – IBM is very specific about the data that will and will not be accepted. For example, no personally identifiable data or personal health information will be permitted into the system – so your constituents’/customers’ PI and PHI data is still secure within your systems.  Neither Lodestar nor IBM will ever see it or have access to it in any way. If you wish for Lodestar to prepare your data for you, we recommend a non-disclosure agreement be in place before getting started.

Because this is a cloud hosted solution, it is priced as a monthly subscription, and there is a tier structure within the pricing, depending on which blueprint you need. Most of the blueprints will allow you to run your model unlimited times per month – but you may have a cap on how many cases you run per month. Standard overages are permitted, but you’ll be charged. You can add to the standard package (i.e. additional questions/predictions to be made) at an additional cost as well. The interesting part about this is when you’re purchasing software to install and use, it is a capital expenditure.  Because this is a subscription service, it can now be documented as an operating expenditure. The price point for Analytic Answer is exceptionally reasonable considering there is no additional expense for training or services – and basically does all the dirty work for you. Furthermore, this is an excellent opportunity to foray into Predictive Analytics as a proof of concept with high ROI at a minimal cost, and provides the ability to present your findings to IT and the upper levels to prove that Predictive Analytics should be more important to your organization.

Next let’s take a look at what questions are available to be answered. IBM has developed specific blueprints that answer specific questions for specific markets:

  • Retail: Purchase Analysis & Offer Targeting
    • Insights for creating combination offers and promotions
    • Targeted product recommendations for individual customers
    • Drive additional purchases and increase spending
    • Assists in adapting to new trends and patterns
  • Non-Profit: Donor Contribution Growth
    • Identify likely prospects for donation
    • How to increase individual donor generosity
    • Right message to right donor at right time
  • Insurance: Renewals
    • Identify policy holders at risk of not renewing
    • Select incentives most likely to retain those likely to churn
    • Prioritize proactive outreach
    • Improve policy holder satisfaction
  • Telco: Churn
    • Identify customers at risk of leaving
    • Determine incentives most likely to persuade individual subscribers to stay loyal
    • Decrease customer churn and increase customer loyalty
  • Debt Collection: Improve Outcomes
    • Determine most and least likely to pay (spend time on those most likely)
    • Recommendation on collection treatment most likely to succeed
    • Increase collection while lowering cost
  • Education: Student Success
    • Identify students at risk
    • Select action most likely to get student back on track
    • Identify patterns in dropout rates and drivers of disengagement

We wish we could tell you more about the stack of technology that IBM has sitting in the cloud that helps produce these results – but the list is long and proprietary to IBM. It is an exceptionally robust set of IBM hardware and software and automated processes and systems that have been developed to get you answers in about a minute when you run your query. With that said, I can say with certainty that the predictive outcomes are produced with IBM SPSS Modeler. If you decide that after your subscription, you would like to move operations in-house and work with Modeler, IBM will provide you with the model built for your organization to support a strong starting point. We recommend training and some services for the smoothest possible transition, and largest Return on Investment (ROI). This transition to in-house analytics will allow for ultimate freedom in data exploration and uncovering other hidden patterns and trends in your organizational data to drive efficiencies, cost savings, and business improvements.

In closing, it is interesting to note that Lodestar can also help you implement the Predictive outcomes into your existing BI solutions, so we are able to assist on the front and back ends of a project like this, making it almost entirely seamless and not requiring much time or effort on the part of your organization. IBM will be continuing to develop new blueprints to be released incrementally over the coming weeks/months/years.  If there is one developed for forecasting, we will also be able to assist in adding these fields into TM1 (as Modeler can now accept TM1 data, add a prediction and confidence interval and output the updated file back to TM1 for consumption).  Stay tuned…not sure if or when that day will come.

If you’d like to learn more about Predictive Analytics Answers and SPSS, please give us a call or send us an email at We would love to work with you!

Leave a Comment

Send this to a friend