Archive for September, 2015

September 23rd 2015

Wise Practitioner – Predictive Analytics Interview Series: Scott Lancaster at State Street Corp.

By: Eric Siegel, Founder, Predictive Analytics World

In anticipation of his upcoming conference presentation, Predictive Analytics for Project Scott_LancasterManagement – Cost Avoidance, at Predictive Analytics World Boston, Sept 27-Oct 1, 2015, we asked Scott Lancaster, Vice President at State Street Corp., a few questions about his work in predictive analytics.

Q: In your work with predictive analytics, what behavior do your models predict?

A: I use the Putnam model for estimating project cost/effort, duration, size, and productivity at a certain level of quality. This model is used for project management and is based on the Rayleigh distribution curve.

Q: How does predictive analytics deliver value at your organization? What is one specific way in which it actively drives decisions?

A: Predictive analytics is used in my IT-related program and project management work to assess the risk of a project and to perform real-time predictive analytical tradeoff analysis of cost, duration, and scope. This allows our business partners to understand the risk involved with a particular project (or portfolio of projects) and make quantitative-based decisions on the so-called triple-constraint tradeoff including:

  • what should be included in the projects’ scope, given a certain timeframe
  • adjust the timeframe given a certain scope and resources
  • adjust resources given the scope and timeframe

Q: Can you describe a successful result, such as the predictive lift of your model or the ROI of an analytics initiative?

A: In the first year we avoided $1.2M of costs by understanding what the high probability of certain projects actual durations were instead of the gut-feel, effort-based estimates which were off by up to a factor of three.

Q: What surprising discovery have you unearthed in your data?

A: Quantifying your project data allows you to accurately assess project risk but you have to look at multiple factors. A lot of projects which look at quantifying duration and effort don’t quantify their scope and that leads to a lot of issues relating to what can really be delivered.

Q: Sneak preview: Please tell us a take-away that you will provide during your talk at Predictive Analytics World.

A: IT project related work is a non-linear function with cost/effort having the least amount of impact to the schedule, yet it’s the first thing projects try to do to meet a deadline. Changing the duration (which is counter-intuitive) actually has the largest impact.

———————

Don’t miss Scott’s conference presentation, Predictive Analytics for Project Management – Cost Avoidance, on Tuesday, September 29, 2015 at 4:20 to 4:40 pm at Predictive Analytics World Boston. Click here to register to attend.

By: Eric Siegel, Founder, Predictive Analytics World

 

 
 

1

 

No Comments yet »

September 8th 2015

Wise Practitioner – Predictive Analytics Interview Series: Jeff Butler at IRS Research, Analysis, and Statistics organization

By: Sean Robinson, Program Chair, Predictive Analytics World for Government

In anticipation of his upcoming conference presentation, The Changing Face of Analytics at Jeff_ButlerFederal Agencies: A View from the IRS at Predictive Analytics World for Government, Oct 13-16, 2015, we asked Jeff Butler, Associate Director of Data Management, IRS Research, Analysis and Statistics organization, a few questions about his work in predictive analytics.

Q: How would you characterize your agency’s current and/or planned use of predictive analytics?  What is one specific way in which predictive analytics actively drives decisions in your agency?

A: The IRS uses a wide range of analytic methods, tools, and technologies to address such problems as ID theft, refund fraud, inventory optimization, and other activities related to its statutory mandates. In an era of persistently reduced budgets, the use of data analytics has become more important than ever to drive innovation, risk management, and decision making across the agency.

Q: Can you describe the challenges you face or have already overcome in establishing a data-driven environment in your agency?

A: Large organizations don’t change their leopard spots overnight. Building a data-driven culture involves fundamental changes to workforce skills and business-IT relationships, which requires change leadership and long-term commitments.

Q: Can you discuss any near term goals you have for improving your agency’s use of predictive analytics?

A: The U.S. taxpayer population has some complexities that present unique challenges to the IRS. For example, high-wealth individuals often behave more like a business, and businesses with connected entities often look more a group of interrelated economic structures than a single business. There is growing interest in network analysis and related methods as an exploratory approach to better understand these types of patterns.

Q: Can you describe a successful result from the employment of predictive analytics in your agency, i.e., cost avoidance, funds recovered, improved efficiency, etc.

A: ID theft remains a significant challenge for the IRS—and therefore for U.S. taxpayers as well. The financial and psychological cost to families whose tax returns are fabricated by ID thieves can be devastating and long lasting. The use of data analytics has allowed the IRS to accelerate the process of verifying ID theft cases for faster case resolution, lowering direct costs through improved automation. Analytic models are also key to detecting and preventing billions of dollars in fraudulent refund claims each year.

Q: Sneak preview: Please tell us a take-away that you will provide during your talk at Predictive Analytics World for Government.

A: Greater awareness is needed by agencies that the traditional paradigm for analyzing data in massively large environments is changing and skills need to adapt. Organizational boundaries between IT and business have to be removed. Greater emphasis needs to be placed on multi-disciplinary teams that combine skills from computer science, IT, statistics, economics, and applied math.

———————

Don’t miss Jeff’s conference presentation, The Changing Face of Analytics at Federal Agencies: A View from the IRS on Tuesday, October 13, 2015 from 10:30 to 11:35 am at Predictive Analytics World for Government.  Click here to register to attend.

By: Sean Robinson, Program Chair, Predictive Analytics World for Government

No Comments yet »

September 2nd 2015

Wise Practitioner – Predictive Analytics Interview Series: Dr. Michael Dulin, Carolinas Healthcare System

By: Jeff Deal, Program Chair, Predictive Analytics World Healthcare

In anticipation of his upcoming keynote conference presentation at Predictive Analytics World Dr Michael_Dulinfor Healthcare Boston, Sept 27-Oct 1, 2015, we asked Dr. Michael Dulin, Chief Clinical Officer for Analytics and Outcomes Research at Carolinas Healthcare System, a few questions about incorporating predictive analytics into healthcare. Catch a glimpse of his keynote presentation, Turning Big Data into Better Care, and see what’s in store for the second annual PAW Healthcare conference in Boston.

Q: In your work with predictive analytics, what area of healthcare are you focused on?

A: Mainly clinical outcomes and quality improvement.  For example, we currently are using predictive models in the areas of readmission risk and length of stay.  These models mainly serve two main purposes:  To predict which patients have a high risk of readmission via model-based risk bands and to proffer interventions based on which variables are loading high in the model.  We are also doing this with length of stay.

Q: What outcomes do your models predict?

A: In addition to the readmission and length of stay models, we just completed state-of-the-art dynamic time-to-event models for hospitalization and developing Type II diabetes.  In the case of hospitalization, we construct patient level survival curves, which capture the amount of time to the event of first hospitalization and their associated probabilities.  In the case of Type II diabetes, we construct survival curves at the patient level for developing diabetes.  With these models, we are also able to see insulating factors in our patient population, which may offer ways of reducing a patient’s probability of hospitalization or developing Type II diabetes.

Q: How does predictive analytics deliver value at your organization? What is one specific way in which it actively drives decisions or impacts operations?

A: One way is through the objective lens of analytics.  We recently completed a purely data driven segmentation of our patient population, where we found seven segments in our population.  Along-side of this, we developed a classification model to score new patients into the segments with very high accuracy.  This allows us to understand the population at a very deep level and optimize care to patients in each segment.  With our classification model, we are able to see the segment migration and understand the variables that drive the migration, which offers possible patient interventions to stop migration to more unhealthy segments.

Q: Can you describe a successful result, such as the predictive lift of your model or the ROI of an analytics initiative?

A: Missing data is always with us.  In an effort to model non-patient probability of having commercial coverage, missing data was a significant impediment to our effort.  Our elite population health analytics team (the special forces of DAA) created and implemented missing data methods to increase the positive prediction of the model by about 35%.

Q: What surprising discovery have you unearthed in your data?

A: In patient discharge data, there was a long held belief in cyclical (seasonality) patterns longer than one week, such as summertime or wintertime effects.  We found there is no statistical evidence of this belief, though the use of spectral decomposition and statistical smoothing.

Q: What areas of healthcare do you think have seen the greatest advances or ROI from the use of predictive analytics?

A: The application of predictive analytics in healthcare is just in its infancy.  Digital healthcare data is doubling about every two years and the amount of semi-structured and unstructured data is increasing as well.  Some of the greatest advances in the future will be in the efficient and meaningful delivery of relevant information for bettering patient care and outcomes, and reducing healthcare costs.

—————————–

Don’t miss Dr. Dulin’s presentation, Turning Big Data into Better Care, at PAW Healthcare on Monday, September 28, 2015 from 1:30 to 2:15 pm. Click here to register for attendance.

By: Jeff Deal, Conference Chair, Predictive Analytics World Healthcare

No Comments yet »