January 16th 2017

Wise Practitioner – Predictive Workforce Analytics Interview Series: Mike Rosenbaum at Arena

By: Greta Roberts, Conference Chair, Predictive Analytics World for Workforce 2017

In anticipation of his upcoming Predictive Analytics World for Workforce conference presentation, Real World Lessons in Predicting Employee Retention and Engagement, we interviewed Mike Rosenbaum, Founder and CEO at Arena. View the Q-and-A below Mike Rosenbaum IMAGEto see how Mike Rosenbaum has incorporated predictive analytics into the workforce at Arena. Also, glimpse what’s in store for the new PAW Workforce conference, May 14-18, 2017.

Q: How is a specific line of business / business unit using your predictive decisions?  How is your product deployed into operations?

A: Our predictions are primarily used by recruiters and hiring managers in hospitals and senior living facilities to identify the applicants who are most likely to provide certain outcomes, like stay in their role, be an engaged employee, provide high quality care, increase patient satisfaction, or be involved in a medical incident. The benefits of these outcomes are primarily felt by a number of business units, including nursing, patient care, food and nutrition, and housekeeping. Our platform is integrated with the client's Applicant Tracking System (ATS) and potential employees are asked to interact with us through a portal that is also hosted on our platform. We use the application data, some limited third party data, and the candidate's behavior on the platform to customize our models for each client, location, and role and to generate predictions for each applicant.

Q: If HR were 100% ready and the data were available, what would your boldest data science creations do?

A: At Arena our mission is to use data to illuminate talent. We aspire to transform the way the healthcare labor market works in a way that makes employers more efficient and employees more fulfilled. We feel that our focus on hiring is a great place to start, and we are expanding through the employee lifecycle to address areas such as team assembly, promotion decisions, time and attendance, and incumbent attrition. Ultimately, we aspire to help organizations transform themselves to address the challenges of a rapidly changing environment. For example, today health care delivery is going through massive changes, with much of the services that have been provided within the four walls of a hospital moving to clinics, retail outlets, offsite medical labs, and ambulatory surgical centers.  Instead of continuing to have people do work that is no longer needed; we investigate whether they might be a good fit for new the roles that are needed.

Q: When do you think businesses will be ready for "black box" workforce predictive methods, such as Random Forests or Neural Networks?

A: In our experience, business people are more interested in the results than in the predictive methods. Our clients are not as interested in reviewing the models or the statistical techniques as they are in seeing how changing their behavior and decisions will affect their outcomes. Of course we continue to internally investigate additional predictive methods to improve accuracy and outcomes.

Q: Do you have suggestions for data scientists trying to explain the complexity of their work, to those solving workforce challenges?

A: The work of a data scientist is undoubtedly complex, but we have found that it is rarely effective to try and explain that complexity to a business person. We have found a focus on results to be the most persuasive way to convince a business person to use predictive analytics. Many times a simple before and after comparison is enough to get over the first hurdle, and providing a well thought out business case with investments, benefits, and return on investment solidifies the case. Sometimes it can help to use an analogy, like credit scoring or voice recognition or book recommendations to show how complex predictions can easily become a part of simple every day decisions. We also find that giving clear guidance on how to use the predictions can help with adoption; many of our predictions are expressed as percentiles, so explaining that the predictions are mean to rank candidates so the most likely to provide the outcome will be the highest, and the least likely will be the lowest.

Q: What is one specific way in which predictive analytics actively is driving decisions?

A: Many of our clients have open positions that attract dozens, if not hundreds, of applicants. The traditional approach to this would be to have recruiters or hiring managers review every applicant and use their individual judgement to decide which are the best to engage in a hiring conversation. Our platform is being used to replace these judgements (which typically contain biases) with predictions to help them engage with the applicants that are most likely to provide the best outcomes. And by using our platform our clients are also able to remove the personal biases and judgements from their hiring process.

Q: How does business culture, including HR, need to evolve to accept the full promise of predictive workforce?

A: While many parts of the business are comfortable with data and analytics, HR is often behind the curve in these capacities. The typical HR employee does not have ready access to data, does not perform their own analysis, and may not be familiar with the key performance indicators that are used to measure their performance. In order to fully recognize the benefits of predictive analytics, the HR workforce itself will need to develop competencies in data and analytics. Luckily they are not the first to make this journey; their colleagues in marketing have been making a similar journey over the last several years and provide an excellent roadmap.

Q: Do you have specific business results you can report?

A: At Arena our clients use our platform in 400+ organizations to process over 4 million applications per year. The median reduction in first year employee turnover all of our clients has been 38%, and when compared to control groups (either other roles in the same facility or the same roles in other facilities) the median improvement is 162%. Because we have a 100% success rate in improving retention, it is easy for us to provide a guarantee to our clients, and so we provide a guarantee to all clients that if we do not reduce employee turnover by 10% in our initial implementation we will refund all money paid to us.

——————

Don't miss Mike’s conference presentation, Real World Lessons in Predicting Employee Retention and Engagement, at PAW Workforce, on Wednesday, May 17, 2017, from 3:30 to 4:15 pm. Click here to register for attendance

By: Greta Roberts, CEO, Talent Analytics, Corp. @gretaroberts and Conference Chair of Predictive Analytics World for Workforce

No Comments yet »

January 13th 2017

Wise Practitioner – Predictive Analytics Interview Series: Darryl Humphrey at Alberta Blue Cross

By: Eric Siegel, Founder, Predictive Analytics World

In anticipation of his upcoming conference presentation, Claim Pattern Anomalies – Making a Mole Hill Out of a Mountain at Predictive Analytics World San Francisco, May 14-18, 2017, we asked Darryl Humphrey, Senior Data Scientists at Alberta Blue Cross, a Darryl Humphrey IMAGEfew questions about his work in predictive analytics.

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

A: Our scope is health, dental, and pharmacy benefit claims submitted by plan members and providers.  Our objective is to reliably gauge the probability that a claim, or series of claims, is / are fraudulent or represent abuse of the benefit plan.

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

A: Obtaining strong evidence of fraud or plan abuse most often requires an on-site investigation and other labor intensive activities.  The result of our analytics materially increases the probability that these efforts will have a positive ROI.

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

A: We have increased the financial recovery per investigation as the analytics indicates which of the behavioral measures are anomalous which facilitates more specific lines of investigation.

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

A: Random forest analyses indicates that some behavioral measures long-held to be important actually don’t contribute much to the differentiating provider claiming patterns.

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

A: Developing an in-house capability (analytics skills, business experience, and tools) has been more cost-effective than using a third-party and is providing a greater analytics depth, breadth, and agility.

———————

Don't miss Darryl’s conference presentation, Claim Pattern Anomalies – Making a Mole Hill Out of a Mountain on Wednesday, May 17, 2017 at 3:30 to 4:15 pm at Predictive Analytics World San Francisco. Click here to register to attend.

By: Eric Siegel, Founder, Predictive Analytics World

No Comments yet »

January 9th 2017

Wise Practitioner – Predictive Workforce Analytics Interview Series: Feyzi Bagirov at 592 LLC and Harrisburg University of Science and Technology

By: Greta Roberts, Conference Chair, Predictive Analytics World for Workforce 2017

In anticipation of his upcoming Predictive Analytics World for Workforce conference presentation, Enhancing the Quality of Predictive Modeling on College Enrollment, we interviewed Feyzi Bagirov, Chief Business Officer at 592 LLC and Analytics Instructor at feyzi-bagirov-imageHarrisburg University of Science and Technology. View the Q-and-A below to see how Feyzi Bagirov has incorporated predictive analytics into the workforce of 592 LLC and Harrisburg University of Science and Technology. Also, glimpse what’s in store for the new PAW Workforce conference, May 14-18, 2017.

Q: How is a specific line of business / business unit using your predictive decisions?  How is your product deployed into operations?

A: One of the ways enrollment departments in higher education are using data science is  identifying students who are most likely to enroll, less likely to enroll and unlikely to enroll. This helps prioritizing marketing efforts. 

Q: If HR were 100% ready and the data were available, what would your boldest data science creations do?

A: Identifying and hiring the right student candidates.

Q: When do you think businesses will be ready for "black box" workforce predictive methods, such as Random Forests or Neural Networks?

A: When businesses will answer these three questions to themselves: 

     1. What questions need to be answered to achieve our objectives? 

     2. What data do we need to answer them? 

     3. How do we get that data?

Q: Do you have suggestions for data scientists trying to explain the complexity of their work, to those solving workforce challenges?

A: Ask them to talk about their business and look for the pain points. Once identified, give a 10,000 feet overview of how the data insight can help in making a decision. 

Q:  What is one specific way in which predictive analytics actively is driving decisions?

A: A monetary outcome (either making or saving) or a public/private benefit of a decision. 

Q: How does business culture, including HR, need to evolve to accept the full promise of predictive workforce?

A: Managers need to realize that:

  1. Data science insights will SUPPORT, but will not MAKE the decisions for them
  2. Utilizing organizational data is more than running descriptive dashboards. Getting into a predictive component quickly is important.
  3. Very few Data Scientists know everything about Data Science. 
  4. Maintaining data quality is important if you want quality insights. Sacrificing data quality for the sake of moving forward needs to be an exception.

——————

Don't miss Feyzi’s conference presentation, Enhancing the Quality of Predictive Modeling on College Enrollment, at PAW Workforce, on Wednesday, May 17, 2017, from 10:15 to 10:35 am. Click here to register for attendance

By: Greta Roberts, CEO, Talent Analytics, Corp. @gretaroberts and Conference Chair of Predictive Analytics World for Workforce

No Comments yet »

January 3rd 2017

Wise Practitioner – Predictive Analytics Interview Series: Craig Soules at Natero

By: Eric Siegel, Founder, Predictive Analytics World

In anticipation of his upcoming conference presentation, Using Predictive Analytics to Improve Customer Retention, at Predictive Analytics World San Francisco, May 14-18, 2017, we asked Craig Soules, CEO & Founder at Natero, a few questions about his work craig-soules-imagein predictive analytics.

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

A: Natero helps its customers by predicting two kinds of potential customer behaviors.  The first is customers who are likely to churn or stop using a given service.  The second is customers who are likely to upsell or purchase more of a given service.

Q: How does predictive analytics deliver value at your organization – what is one specific way in which it actively drives decisions or operations?
 
A: Predictive analytics is a key way in which our customers decide which customers to reach out to and work with.  By focusing on the customers who are likely to change their use of the service (either churn or upsell), they can have the most positive effect on the health of their business.

Q: Can you describe a quantitative result, such as the predictive lift of your model or the ROI of an analytics initiative?
 
A: Customers using Natero have been able to reduce their customer churn by as much as 24% month-over-month.  Although churn reduction is ultimately achieved through the efforts of the customer success team and their engagement with the customer's needs, knowing which accounts to spend time with is a critical factor in spending those efforts wisely.  Predictive analytics play a key role in driving their attention and efforts in the right ways.

Q: What surprising discovery or insight have you unearthed in your data?
 
A: One surprising discovery is the role that individual user data plays in understanding account churn.  A lot of customer success teams today rely on high-level metrics such as DAU and MAU to understand account health, but those are almost never enough to be truly predictive.  In the end, the behaviors of individual users and the changes in those individual behaviors are often required to build accurate models of churn outcomes.

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

A: Predictive models really need to be tuned not just to the use case, but to the individual scenario.  As such it's critical to gather feedback from the users of the model results on an ongoing basis to continue to tune those results toward the specifics of their use case.

———————

Don't miss Craig’s conference presentation, Using Predictive Analytics to Improve Customer Retention, on Tuesday, May 16, 2017 from 10:55 to 11:15 am at Predictive Analytics World San Francisco. Click here to register to attend.

By: Eric Siegel, Founder, Predictive Analytics World

No Comments yet »

December 28th 2016

Sound Data Science: Avoiding the Most Pernicious Prediction Pitfall

es-blog-post-image-12-28-2016

By Eric Siegel, Predictive Analytics World

Original published in OR/MS Today

In this excerpt from the updated edition of Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie, or Die, Revised and Updated Edition, I show that, although data science and predictive analytics’ explosive popularity promises meteoric value, a common misapplication readily backfires. The number crunching only delivers if a fundamental—yet often omitted—failsafe is applied.

Prediction is booming. Data scientists have the “sexiest job of the 21st century” (as Professor Thomas Davenport and US Chief Data Scientist D.J. Patil declared in 2012). Fueled by the data tsunami, we’ve entered a golden age of predictive discoveries. A frenzy of analysis churns out a bonanza of colorful, valuable, and sometimes surprising insights:

• People who “like” curly fries on Facebook are more intelligent.

• Typing with proper capitalization indicates creditworthiness.

• Users of the Chrome and Firefox browsers make better employees.

• Men who skip breakfast are at greater risk for coronary heart disease.

• Credit card holders who go to the dentist are better credit risks.

• High-crime neighborhoods demand more Uber rides.

Look like fun? Before you dive in, be warned: This spree of data exploration must be tamed with strict quality control. It’s easy to get it wrong, crash, and burn—or at least end up with egg on your face.

In 2012, a Seattle Times article led with an eye-catching predictive discovery: “An orange used car is least likely to be a lemon.” This insight came from a predictive analytics competition to detect which used cars are bad buys (lemons). While insights also emerged pertaining to other car attributes—such as make, model, year, trim level, and size—the apparent advantage of being orange caught the most attention. Responding to quizzical expressions, data wonks offered creative explanations, such as the idea that owners who select an unusual car color tend to have more of a “connection” to and take better care of their vehicle.

Examined alone, the “orange lemon” discovery appeared sound from a mathematical perspective. Here’s the specific result:

This shows orange cars turn out to be lemons one third less often than average. Put another way, if you buy a car that’s not orange, you increase your risk by 50%.

Well-established statistics appeared to back up this “colorful” discovery. A formal assessment indicated it was statistically significant, meaning that the chances were slim this pattern would have appeared only by random chance. It seemed safe to assume the finding was sound. To be more specific, a standard mathematical test indicated there was less than a 1% chance this trend would show up in the data if orange cars weren’t actually more reliable.

But something had gone terribly wrong. The “orange car” insight later proved inconclusive. The statistical test had been applied in a flawed manner; the press had ran with the finding prematurely. As data gets bigger, so does a potential pitfall in the application of common, established statistical methods.

The Little Gotcha of Big Data

The trouble with the world is that the stupid are cocksure and the intelligent are full of doubt.

—Bertrand Russell

Big data brings big potential—but also big danger. With more data, a unique pitfall often dupes even the brightest of data scientists. This hidden hazard can undermine the process that evaluates for statistical significance, the gold standard of scientific soundness. And what a hazard it is! A bogus discovery can spell disaster. You may buy an orange car—or undergo an ineffective medical procedure—for no good reason. As the aphorisms tell us, bad information is worse than no information at all; misplaced confidence is seldom found again.

This peril seems paradoxical. If data’s so valuable, why should we suffer from obtaining more and more of it? Statistics has long advised that having more examples is better. A longer list of cases provides the means to more scrupulously assess a trend. Can you imagine what the downside of more data might be? As you’ll see in a moment, it’s a thought-provoking, dramatic plot twist.

The fate of science—and sleeping well at night—depends on deterring the danger. The very notion of empirical discovery is at stake. To leverage the extraordinary opportunity of today’s data explosion, we need a surefire way to determine whether an observed trend is real, rather than a random artifact of the data. How can we reaffirm science’s trustworthy reputation?

Statistics approaches this challenge in a very particular way. It tells us the chances the observed trend could randomly appear even if the effect were not real. That is, it answers this question:

Question that statistics can answer: If orange cars were actually no more reliable than used cars in general, what would be the probability that this strong a trend—depicting orange cars as more reliable—would show in data anyway, just by random chance?

With any discovery in data, there’s always some possibility we’ve been Fooled by Randomness, as Nassim Taleb titled his compelling book. The book reveals the dangerous tendency people have to subscribe to unfounded explanations for their own successes and failures, rather than correctly attributing many happenings to sheer randomness. The scientific antidote to this failing is probability, which Taleb affectionately dubs “a branch of applied skepticism.”

Statistics is the resource we rely on to gauge probability. It answers the orange car question above by calculating the probability that what’s been observed in data would occur randomly if orange cars actually held no advantage. The calculation takes data size into account—in this case, there were 72,983 used cars varying across 15 colors, of which 415 were orange.

Calculated answer to the question: Under 0.68%

Looks like a safe bet. Common practice considers this risk acceptably remote, low enough to at least tentatively believe the data. But don’t buy an orange car just yet—or write about the finding in a newspaper for that matter.

What Went Wrong: Accumulating Risk

In China when you’re one in a million, there are 1,300 people just like you.

—Bill Gates

So if there had only been a 1% long shot that we’d be misled by randomness, what went wrong?

The experimenters’ mistake was to not account for running many small risks, which had added up to one big one…

Click here to access the complete article as originally published in OR/MS Today

 

Eric Image 2015 croppedAdapted with permission of the publisher from Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie, or Die, Revised and Updated Edition (Wiley, January 2016) by Eric Siegel, Ph.D., who is the founder of the Predictive Analytics World conference series (cross-sector events), executive editor of The Predictive Analytics Times, and a former computer science professor at Columbia University.

No Comments yet »

December 23rd 2016

Wise Practitioner – Predictive Analytics Interview Series: Ashish Bansal and John Schlerf from Capital One

By: Eric Siegel, Founder, Predictive Analytics World

In anticipation of their upcoming conference co-presentation, The Quest for Labeled Data:  Integrating Human Steps, at Predictive Analytics World San Francisco, May 14-18, 2017, we asked Ashish Bansal, Senior Director, Data Science and John Schlerf, Data ashish-banal-imageScientist at Capital One, a few questions about their work in predictive analytics.

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

A: These models are used to match credit card transactions to augmented merchant data to improve readability of online credit card statements.jeff-schlerf-image

Q: How does predictive analytics deliver value for your customers – what is one specific way in which it actively improves operational outcomes?

A: Customers expect their bank to know the merchants where they shop. By expanding that knowledge beyond just the merchant name, we can improve our customers’ brand perception and loyalty. This also lowers operational call center costs, as customers can access more details about where they made a purchase.

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

A: We increased our library of known restaurants by over 10% in less than 1 week.
 
Q: What surprising discovery or insight have you unearthed in your data?
 
A: We were quite surprised by the vibrancy of the communities of micro-workers. They take real pride in their work, and deliver very high quality output.

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

A: Human judgement is often the best source of labeled data for training and testing complicated models. Collecting such data at scale can be daunting. This talk focuses on building automated data pipelines that integrate manual labeling steps.

———————

Don't miss Ashish and John’s conference co-presentation, The Quest for Labeled Data:  Integrating Human Steps on Wednesday, May 17, 2017, from 11:15 am to 12:00 pm at Predictive Analytics World San Francisco. Click here to register to attend.

By: Eric Siegel, Founder, Predictive Analytics World

No Comments yet »

December 19th 2016

Wise Practitioner – Predictive Analytics Interview Series: Kristina Pototska at TriggMine

By: Eric Siegel, Founder, Predictive Analytics World

In anticipation of her upcoming conference presentation, 7 Examples of Customer Retention with Predictive Email Marketing at Predictive Analytics World San Francisco, May 14-18, 2017, we asked Kristina Pototska, CMO at TriggMine, a few questions about kristina-pototskaya-imageher work in predictive analytics.

Q: In your work with predictive analytics, what behavior or outcomes did your models predict?

A: We launched predictive analytics for eCommerce websites with the goal of dramatically increasing customer retention. We aimed for a specific target audience, boosted engagement, reduced turnover rates, drove more conversions and increased revenue for every email campaign our clients ran.

Q: How does predictive analytics increase profits? Name one specific way in which it directly drives customer decisions.

A: Our Company provides email marketing automation for eCommerce, which isn't really new to the market. And there should always be room for improvement. That's why we started with predictive analytics, which we knew would deliver greater personalization and increased revenue for every email campaign we send. Now, predictive analytics is one of our standout features, the one that offers the best value for our customers.

Q: Can you describe a quantitative result, such as your model's predictive increase or ROI from an analytics campaign?

A: The first email campaign we optimized using predictive analytics was abandoned carts recovery. We had a 100% conversion increase in the first month alone — same for the click-rate.

Following that, we implemented predictive technologies in our other email campaigns and saw the same fantastic results. Now, our customers are seeing an average ROI hovering at about 2000%.

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

A: The first discovery for me was the amount of data we already had. We'd been collecting it over a three-year period but never touched it. However, when we started to analyze that data, we were suddenly able to create in-depth customer profiles, including portraits of and predictions for the lifetime value of each customer, their click rates, as well as their likelihood of purchasing or abandoning their carts.

That's when I discovered the incredible power of predictive technology.

Q: Sneak preview: Please give us a take-away you'll later (also) provide during your talk at Predictive Analytics World.

A: The attendees will be able to implement our proven technology, already tested on eCommerce websites in order to send more personalized and behavior-based emails, create in-depth customer profiles and lookalike portraits, present better offers that customers are more likely to click, decrease abandonment and increase revenue with every email they send.

My presentation offers case-studies that will show attendees well-tested methods for vastly improving their email marketing — even if they don't think they need it.

———————

Don't miss Kristina’s conference presentation, 7 Examples of Customer Retention with Predictive Email Marketing on Tuesday, May 16, 2017 at 11:20 to 11:40 am at Predictive Analytics World San Francisco. Click here to register to attend.

By: Eric Siegel, Founder, Predictive Analytics World

No Comments yet »

December 16th 2016

Wise Practitioner – Predictive Analytics Interview Series: Frederick Guillot at The Co-operators General Insurance Company

By: Eric Siegel, Founder, Predictive Analytics World

In anticipation of his upcoming conference presentation, Defining Optimal Segmentation Territories – 10 Years of Research at Predictive Analytics World San Francisco, May 14-18, 2017, we asked Frédérick Guillot, Senior Manager, Research and Innovation at Frederick Guillot ImageThe Co-operators General Insurance Company, a few questions about his work in predictive analytics.

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

A: At the Co-operators, we leverages predictive modeling for many purposes. We are using more traditional models to quantify the insurance risk of our clients. We also leverages more advanced techniques such as propensity model to maximize client engagement.

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

A: Most pricing decisions regarding our insurance products are backed by predictive modeling. Predictive models also allow us to be more agile in many operational areas such as in the buying process, or the settlement of claims.

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

A: Mixing traditional predictive modeling with geospatial analytic and Big Data is a very fertile research area for insurers. We spent more than 10 years so far in refining the way we are defining our segmentation territories, and each improvement translates into tangibles benefits for the organization. Over time, we managed to triple our territories’ homogeneity.

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

A: On the perspective of creating segmentation territories, I definitely think that the increasing availability of geospatial open data now enable many more opportunities for improving models and get more accurate predictions of insurance risk.

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

A: If you are not a little shy about a new predictive modeling application you are launching within your organization, you probably wait too long before releasing it. The territory analysis I will present in my talk is a good illustration of the minimum viable product mindset in which you better launch fast, and iterate over time to grow your model accuracy.

———————

Don't miss Frédérick’s conference presentation, Defining Optimal Segmentation Territories – 10 Years of Research on Wednesday, May 17, 2017 from 11:40 am to 12:00 pm at Predictive Analytics World San Francisco. Click here to register to attend.

By: Eric Siegel, Founder, Predictive Analytics World

No Comments yet »

September 30th 2016

Wise Practitioner – Predictive Analytics Interview Series: Robin Thottungal at U.S. Environmental Protection Agency

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

In anticipation of his upcoming conference keynote presentation, 21st Century Data-Driven Environmental Protection at Predictive Analytics World for Government, October 17-20, 2016, we asked Robin Thottungal, Chief Data Scientist/Director of robin-thottungalAnalytics at the U.S. Environmental Protection Agency (EPA), 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: Every day, EPA tackles enormous challenges to protect human health and the environment. And now we realize that strategy alone is no longer adequate to address the diverse circumstances that we face in America, such as our changing climate or the risk of chemical explosions. We want to do better.

We are learning that, while technology cannot replace strategy, strategy needs to work hand in hand with a data-driven approach. So we are putting our data to work, using technology to better serve the American people.

One of our plans is to employ predictive analytics to prevent catastrophes and to reduce response times downstream. For example, could real-time monitors at underground storage tanks prevent a chemical spill?

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

A: Leaders at the EPA are routinely faced with challenging situations. My question is: how do you create a culture within leadership where decisions are backed by data? One of my goals is to inspire our leadership to make data a critical part of their decision making process. I want them to instinctively ask about the data behind all proposals.

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

A: We are connecting our vision with our values so that all of our activities align with our mission. And this is possible by following a simple recipe: 1) develop tech-talent within EPA staff; 2) invest in the right technology that works on large volume datasets; and 3) adjust our processes to support predictive analytics.

We took inspiration from tech start-ups. If you mix talent with technology without defining a clear path forward, the right processes evolve naturally. Over time, we will become capable of asking questions that we cannot even think to ask today.

Q: Can you describe a successful result from the employment of predictive analytics in your agency?

A: Across the board, data is driving decisions at EPA. As a result, we are seeing serious improvements in our operational efficiency. This is very exciting because we are not in the business of tackling one specific problem; among other things, we regulate air emissions, we monitor water quality, we fund innovation, and we set standards on chemicals to protect the health of all Americans.

By engraining the spirit of predictive analytics across the enterprise, it seems like everything is changing at the same time. From improved administrative processes to an informed Flint Safe Drinking Water Task Force, efficiencies abound.

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

A: You can use bureaucracy to your advantage if you take a different approach. By thinking like a start-up, my team has been successful at disrupting the typical way of doing business in EPA. We experiment, select the best minimum viable products, scale them up and iterate.

———————

Don't miss Robin’s conference presentation, 21st Century Data-Driven Environmental Protection  on Monday, October 17, 2016 from 9:15 to 10:00 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 23rd 2016

Wise Practitioner – Predictive Analytics Interview Series: Miguel Castillo at U.S. Commodity Futures Trading Commission

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

In anticipation of his upcoming conference co-presentation, Words that Matter:  Application of Text Analytics at the U.S. Commodity Futures Trading Commission, at Predictive Analytics World for Government, October 17-20, 2016, we asked Miguel miguel-castillo-imageCastillo, Assistant Inspector General for Audit at U.S. Commodity Futures Trading Commission, 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 agency recognizes that data and technology is critical to transform the CFTC into a 21st century regulator that can efficiently and cost-effectively surveil the derivatives markets. In its Strategic Plan, Goal 1 for IT is to deliver services aligned with core mission functions of the CFTC. Its priority is to meet business needs first by empowering users with self-service technology platforms for data analysis, then by enterprise-focused automation services.  The extensive research and analytical backgrounds of its senior economists also ensures that analyses reflect the forefront of economic knowledge and econometric techniques.  Staff expertise is grounded in a solid knowledge of market institutions and practices and experience communicating the results of quantita­tive analysis.

So while the agency is building its infrastructure, collecting market data, and hiring competent economists, there is an opportunity to introduce predictive sciences into the mix.

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

A: One challenge is changing the business culture to balance data access with information security.  We are testing an MOU to meet this challenge.

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

A: Collaborate, collaborate, and collaborate on projects that use analytics to determine use cases for “predictive analytics.”  I think it’s a matter of time before the agency fully learns from the experience of using data to its advantage.

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: Our audit text mining experiment used a simple mathematical approach using historical reports to understand how to better plan audits.

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

A: Not only will we discuss our audit planning text mining experiment but also another effort related the agency’s rule-making.

———————

Don't miss Miguel’s conference presentation, Words that Matter:  Application of Text Analytics at the U.S. Commodity Futures Trading Commission, on Tuesday, October 18, 2016, from 10:30 to 11:20 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 »

Next »

  • Subscribe Via Email

    Get a daily digest of new posts delivered to your inbox:

  • Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie, or Die
    BOOK AWARDS:
  • Recent Posts