Could Predictive Analytics Have Prevented 13 Deaths?

The families of those who died in General Motors cars containing defective ignition switches want prosecutors to go after General Motors insiders responsible for letting the problem fester for more than a decade.  Some would argue that it’s a cover-up.  With advanced technology today, software that provides Predictive Analytics can help car manufacturers identify and modify production that could ultimately find defects faster, or avoid them altogether.

As an attorney and expert in Business Analytics business law, I have to question if Predictive Analytics will change the level of responsibility manufacturers have.  Other auto companies leverage technology to identify and fix defects.  One major car company utilizes vast amounts of data (Big Data) and IBM Predictive Analytics software (SPSS) to find unforeseeable relationships that lead to the discovery of defects they can fix by modifying their production process.  Here’s a quick link for reference:

Predictive Analytics and Big Data allow companies to identify relationships in huge amounts of data that may never have been discovered without this advanced technology. By identifying unforeseen relationships, companies can use analytics to predict maintenance needs on planes, trucks, plant equipment, etc.

But could it save lives?

While it’s unknown if GM utilizes the advanced technology of Predictive Analytics, the question remains; could this technology have prevented the loss of life?  There is a lot of research that shows Predictive Analytics can identify relationships leading to the discovery of defects in products, trend purchasing behavior, and even predict if a teenage girl is pregnant before the family knows. ( )

I believe only time will tell how many lives can be saved by data and analytics, but, theoretically, it could be significant.  Businesses are in the infancy of leveraging the vast amounts of data they are collecting and their analytics tools. The possibilities are endless. 

We CAN Change the World with Analytics!

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!

Introduction to Predictive Analytics with IBM SPSS – Part I

Most folks who know about SPSS are aware of it because they took a Statistics class in college and used IBM SPSS Statistics. It is a favorite among professors for teaching due to its easy to learn interface and the fact that the user doesn’t need to learn any coding language.

What’s not widely known is that there’s MUCH MORE than IBM SPSS Statistics in the brand family!

Because there is a lot to cover, I’m going to split this into “Beginner” and “Advanced” – this is aligned with the analytical maturity blog published earlier, so check where you are before you dive in.

The items listed in this “Beginner” post are more geared towards folks with little to no experience or exposure – maybe working in spreadsheets but interested in “getting predictive”.

IBM Analytic Answers: This new little gem is about as easy as predictive analytics gets. There are several very specific blueprints that IBM has developed for very specific needs: Insurance Renewals, Donor Contribution Growth, Prioritized Collections, Retail & Offer Targeting, Student Retention, and Telco Churn prevention. The tag line for this gem is “if you know how to upload a picture to Facebook – you can do predictive analytics!” IBM hosts this offering in a SaaS model – you just log into a webpage and upload a CSV file with variables pre-specified by IBM, and click submit. About a minute later, a file is returned to you with a prediction, a confidence interval, and an action. IBM won’t accept any personally identifiable information so your data is very secure, and it will take them about 2 weeks to build the model for you once you’ve signed up. When you submit a file, it runs against a Modeler (see below) instance in the cloud, and through a Modeler stream that IBM has created specifically for your data. Lodestar (as an IBM Business Partner) can offer services adjacent to this offering and can prep and submit the data for you, as well as provide results in a framework that will snap-fit into your business (i.e. Cognos Dashboard, etc). Pricing will vary depending on which blueprint(s) you need, any additional data you’d like to run, and how many cases you want to run against the model per month. This is a VERY cost effective launch for an organization that is interested in “getting predictive” but doesn’t know where to start.

IBM SPSS Data Collection: This family is the soup to nuts survey tool offered by IBM. Here you can create a survey and deploy it in multiple modes; paper, web, phone, mobile, even manual data entry. It also has a reporting feature available to keep you up to date with your progress. There is a Text Analytics component as well. This allows you to put those open ended responses to work by providing valuable sentiment analysis and allowing you to make that qualitative data into quantitative data to boost the accuracy of any models you might create with the data. When speaking about licensing, it is modular, so you don’t need to buy any capabilities you don’t require and can create a snap-to-fit survey solution.

IBM SPSS Statistics: This is the old familiar spreadsheet-looking package you might remember from college. The licensing methodology is modular, so there is the Base and fourteen modules to choose from. IBM was kind enough to analyze SPSS Statistics customers’ buying habits and has created discounted bundles that align to various common analysts’ needs: Base, Standard, Professional and Premium. There are a few stand-alone products in this family: Sample Power and Viz Designer. IBM SPSS Statistics is an excellent way to avoid common errors found in spreadsheets and has many capabilities for data cleansing, organizing, and modeling. In the most recent releases, IBM has added Monte Carlo simulation.  It furnishes the decision maker with a range of possible outcomes, along with how probable that outcome is (confidence score). Statistics is friendly with open source R algorithms.  They can even be stored in the drop down menu, so any algos that don’t come stock can be added at any time. If you’re a Statistics customer already and notice that your jobs are running slow (usually due to a very wide data set, or just very large – peta bytes or terabytes) there is a server component that can be added. This component pushes the “crunching” to the server for additional power, and when the job is finished, the results are sent back to the client. We can help you design a statistical package that meets your needs, so just let us know.

IBM SPSS Modeler: This data mining workbench is the world class gold standard. While Statistics is great for proving a hypothesis, Modeler is more focused on hypothesis generation and allowing a user to uncover complex and hidden patterns and trends in large data sets. To be clear, this workbench is not a “black box” technique as many claim data mining to be – and while it’s the easiest data mining software on the market, one should most certainly invest in learning how to use it and why someone would choose one course of action over another. The workbench, unlike Statistics, begins as a blank canvas.  The user pulls in icons from the tray at the bottom and connects them into a stream or workflow. Modeler is data agnostic and friendly with any ODBC compliant source. Some capabilities included in modeler are data cleansing, data merging, auto modeling, auto clustering, social analytics, entity resolution, text analytics and much, much more. Modeler is available in two “flavors”: Professional (quantitative), and Premium (qualitative, entity resolution, social analytics, etc.). Like Statistics, if you’re a Modeler user already and have jobs that are taking too long to crunch there is a server component available. This is a good idea if you have very wide data sets, or are trying to crunch petabytes or terabytes (or more) of data.

Again – these are all good starting places. Lodestar can help you identify which, if any, would be useful for your organization. Please contact us to get started on the path to Predictive!

You can now see Part 2 of our SPSS Product Family Overview HERE.

Predictive Analytics For Retail Industry

Understanding and winning customers isn’t easy, especially in this constantly changing marketplace. The problem isn’t lack of data. Data pours in from multiple systems including social media. The challenge is how to extract meaning from it to inform decision-making and enable productivity and agility in the face of market demands. Check out how IBM SPSS software is making Predictive Analytics For Retail Industry work.

IBM Cognos software is one way in which organizations are leveraging new intelligence to create a competitive advantage. IBM Cognos Analytics and Performance Management solutions provide a planning, consolidation and business intelligence platform that helps companies plan, understand and manage financial and operational performance. With capabilities including reporting, analytics, dashboards, planning, scorecards and more, companies can understand performance and make better decisions.

Retail operations generate huge amounts of transactional information, which provide details on product purchase patterns and individual customers or customer profiles. Most retail companies acquire this data either from their customers through rewards programs or from market agencies such as Facebook and Twitter. The sheer volume of data makes consumer buying patterns difficult to detect by manual means, and companies wind up failing to gain any benefit from all this data.

IBM SPSS Market Basket Analysis uses algorithms to analyze this transaction and customer data, relate it to previous purchases and build predictive models that can be applied to:

  • Decide what categories or products to display or promote together.
  • Decide whether an offer is valid for a particular customer.
  • Predict the probability that the customer will respond to the offer.
  • Calculate the value of the customer accepting the offer.

Applying these models allows you to select which one is best for each customer or customer segment. These selections are then delivered to shoppers in the most appropriate way either through emails, directly to their smart devices or loyalty card holders might receive targeted coupons with their monthly statement.

With IBM Cognos software, you can ensure your product offers and promotions match shopper preferences and behavior, so you can maximize the return on market spending. By linking purchases to individual purchasers, you can take this even further by tailoring offers to specific customer segments and driving higher returns from more precisely targeted campaigns.

For more information on how IBM Cognos can help your retail organization, contact Lodestar Solutions.

Heather Cole 813-415-2910

IBM SPSS Predictive Analytics – Predicting the Future

IBM Business Analytics software is designed to deliver complete, insightful, and accurate information for decision makers to make more effective decisions. As part of this portfolio, IBM SPSS Predictive Analytics software specializes in predictive analytics which organizations can rely on to predict future outcomes based on patterns found in historical data. State and Local Government, Multi-National Corporations of all sizes can benefit from the IBM SPSS technology to provide insight into current performance. They can also leverage the predictive capabilities to be better prepared for what is around the corner. Business Intelligence can help monitor current and past performance while Predictive Analytics can answer why the business is performing in a certain manner and how it can be improved in the future.

Organizations that incorporate IBM SPSS Predictive Analytics solutions into their daily operations are able to predict with a high level of certainty the result of options before they even make the decision. It can ensure that the right decisions are made, every time, at the appropriate point of customer interaction. For example, multiple cities around the United States are using predictive analytics to prevent crime by stationing police in high crime areas at historically problematic times to act as a deterrent to crime. Predictive Analytics can help organizations to gain a better understanding of various types of business processes and ultimately have a major impact on decisions that have a positive impact on company’s profitability.

IBM SPSS Data Collection

IBM SPSS Data Collection is a comprehensive survey management solution that empowers organizations to capture customer’s feedback from multiple channels including online, phone, and in person. It offers the capability to manage the entire survey process from design and data collection through analysis of the end results. By applying real time logic and data validation, organizations can make decisions faster and react to customer demands more effectively.

IBM SPSS Statistics

IBM SPSS Statistics is widely used by professionals in commercial, governmental agencies, and academic organizations worldwide. It is used to solve complex business problems, predict patterns to prevent crime, and anticipate demand based upon seasonal weather patterns.

The IBM SPSS Statistics suite of tools includes a set of components for data entry, data management, data preparation/transformation, statistical analysis, analytics procedures and reporting functions. It can take data from almost any type of file and use it to generate tabular reports, plots of distributions and trends, descriptive statistics, and complex statistics models. Customers are using IBM SPSS Statistics to test and validate assumptions faster, discover information more efficiently, and predict with a high degree of certainty what the most likely outcome will be.

IBM SPSS Modeler

Include information from unstructured data such as web activity, blog content, customer feedback, emails, and articles, along with structured numerical data to create the most accurate predictive models possible. Advanced natural language processing techniques enable users to extract key concepts, sentiments, and relationships from unstructured data and convert them to a structured format for predictive modeling.