Archive for December, 2014

December 31st 2014

Wise Practitioner – Predictive Analytics Interview Series: Bryan Guenther of RightShip

By: Eric Siegel, Founder, Predictive Analytics World

 

In anticipation of his upcoming conference presentation,

The Impact of Predictive Analytics on Maritime Safety and Efficiency, at Predictive Analytics World San Francisco, March 29-April 2, 2015, we asked Bryan Guenther, Qi Program Manager at RightShip, a few questions about his work in predictive analytics.

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

A: In essence our models predict the likelihood of an incident at sea. We are also developing other models to predict specific kinds of shipping accidents, e.g., accidents that cause pollution, ships running aground, etc.; as well as models that drive efficiency – e.g., in loading/unloading at port.

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

A: As we work in the services industry, our customers – who use our models for their vessel selection – are the ones that ultimately get the value from the models (which they then pay us for).

Predictive analytics provides us with the ability to identify vessels that may have an incident, and therefore remove them from our customers’ supply chain – so indirectly we are reducing the likelihood of a vessel having an accident. As such it’s not just about money: the value our analytics provides is about limiting risk, saving lives, and reducing environmental damage.

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

A: Each time our customer avoids an unsafe vessel it’s a ROI, and a success, so the prediction actually does this. In 2013 alone we removed over 950 vessels from customer supply chains – so we see that as potentially 950+ incidents that were avoided.

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

A: Analytics showed us the complexity of the relationships between various factors. If you take age as an example, we previously had assumed this to be a fairly linear factor that operated independently; however predictive analytics showed us this is not the case. We discovered that the way age affects a vessel is dependent on a lot of other factors such as tonnage, past casualty history, owner, manager, parent, flag, class, crew, etc.  There are many complex relationships and interactions.

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

A: I’ll provide some practical examples of how predictive modelling has made a real difference. Our next predictive model may save someone’s life, keep oil out of the water & birds in the air! I must say that although our prescriptive model has done a fantastic job so far in reducing casualties; predictive modelling will take us to the next level. This transition is being driven through technology – we can’t move on and improve with old technology.

Don't miss Bryan Guenther’s conference presentation, The Impact of Predictive Analytics on Maritime Safety and Efficiency, at Predictive Analytics World San Francisco, on Tuesday, March 31, 2014 from 11:45 am-12:05 pm.  Click here to register for attendance.

By: Eric Siegel, Founder, Predictive Analytics World

Eric Siegel, Ph.D., founder of Predictive Analytics World and Text Analytics World, and Executive Editor of the Predictive Analytics Times, makes the how and why of predictive analytics understandable and captivating. He is the author of the bestselling, award-winning Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie, or Die, a former Columbia University professor, and a renowned speaker, educator, and leader in the field. 

No Comments yet »

December 23rd 2014

Wise Practitioner – Predictive Analytics Interview Series: Aaron Lanzen of Cicso

Wise Practitioner – Predictive Analytics Interview Series: Aaron Lanzen of Cicso

By: Eric Siegel, Founder, Predictive Analytics World

In anticipation of his upcoming conference presentation, Integrating Predictive Models within a Rules Engine for Resource Allocation, at Predictive Analytics World San Francisco, March 29-April 2, 2015, we asked Aaron Lanzen, Solutions Architect – Business Rules & Analytics at Cisco, a few questions about his work in predictive analytics.

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

A:  Most of the rules and all of our behind-the-scenes modeling activities are designed to give the engine as much “situational awareness” as possible to accurately predict engineer, customer, product, and system behaviors.  The goal is to align “reality” with our global strategy including unique regional dynamics.  One simple example is determining support engineer “availability.”  We use two separate models to calculate a live likelihood that any given engineer is “ready” for new work and capable of handling the call. 

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

A:  These models work across the organization and force alignment between planning and execution. The support engineer availability model is a great example.  We predict two components: Shift information, which provides the “supply” of engineers and “handle time” to determine engineer readiness after taking any type of work.  When you put these together you have valuable understanding of human behavior that helps align resources in a live decision plus it provides the foundation for strategic headcount planning.       

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

A:  While I cannot explain specific models or goals because of IP/trade secret issues, I can give you a broad example.  In one of our models, we choose a small number of available and qualified engineers to see a case and then allow one of those engineers to accept it.  Our previous approach was to show the case to many engineers at once; but if you show it to 200 people, we found no one really felt accountable.  Our simple “availability model” allowed Cisco to successfully reduce the number of engineers who see a case from 180 to 5!  This drives accountability and much better strategic alignment between the engineer and work. 

Q:  What surprising discovery came about during this project?

A:  My biggest surprise was how quickly a global organization can align once you provide the ability to handle objections.  We took it upon ourselves to quantify and clearly model the stakeholders’ objections and assumptions they felt would impact their portion of the business.  Sometimes we learned; other times we were able to prove no relationship existed.  The process of defining an objection versus simply allowing an opinion to hold back progress is magical.  This behavior drives incredibly productive conversations that we named “the fact based conversation.”

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

A:  People, their thoughts, insights, and objections are incredibly important to any decision-based project.  Predictive models cannot really replace people, but if they are used properly, they can be a powerful tool in aligning or influencing an organization to make a successful, fact-based decision.   The real secret is to create synergy between your thought leaders and your technical capabilities like rule engines and predictive models.

Don't miss Aaron Lanzen’s conference presentation, Integrating Predictive Models within a Rules Engine for Resource Allocation, at Predictive Analytics World San Francisco, on Tuesday, March 31, 2015, from 4:45-5:30 pm. Click here to register for attendance.

By: Eric Siegel, Founder, Predictive Analytics World

Eric Siegel, Ph.D., founder of Predictive Analytics World and Text Analytics World, and Executive Editor of the Predictive Analytics Times, makes the how and why of predictive analytics understandable and captivating. He is the author of the bestselling, award-winning Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie, or Die, a former Columbia University professor, and a renowned speaker, educator, and leader in the field. 

No Comments yet »

December 16th 2014

Wise Practitioner – Predictive Analytics Interview Series: David Schey of Digitas

Wise Practitioner – Predictive Analytics Interview Series:  David Schey of Digitas

By: Eric Siegel, Founder, Predictive Analytics World

In anticipation of his upcoming conference presentation, Uplift Modeling Versus Traditional Response Modeling – Which One is Right for You?, at Predictive Analytics World San Francisco, March 29-April 2, 2015, we asked David Schey, Senior Director, Analytic Consulting Group, Digitas, a few questions about his work in predictive analytics.

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

A:  We model a wide variety of behaviors including response, attribution, spending, attrition, ‘clone’, customer value, market basket, fraudulent activity, next most logical product/product lifecycle, insurance claims, and a variety of credit evaluation dimensions.

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

A:  Predictive analytics delivers a superior experience to our client’s customers. By more actively engaging with customers, we optimize the customer experience, increase retention rates, and enhance spending patterns. Our models help managers deliver the right message to the right customers through the right medium. Contact decisions are frequently made based solely on some of the models referred to above.

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

A:  A major retailer found that control groups were performing in line with mailed groups. Although response models were used, they did not provide the incremental lift that the retailer was expecting. Out uplift model resulted in identifying 20% of the mailed population that provided 16.5 basis point lift, a result that the retailer had never experienced.

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

A: The primary lesson is not to take data at face value! During one exercise for an auto manufacturer, we found that 39% of our clients’ customer base owned 9 cars! Seems outlandish, and it was. The value ‘9’ was used as missing value indicator. If it’s too good to be true-it isn’t.

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

A:  There’s more than one way to skin a cat. While there are several approaches for developing uplift models, not all of them provide satisfactory results all the time.  Also, uplift models provide a completely new lens by which direct marketers will increase the sophistication of their contact strategy.  The concept of not "waking a sleeping dog" (i.e. customers that are negatively influenced by communications) is often foreign to traditional direct marketing principals…not only will you increase profit by suppressing certain customers, but those funds can be reallocated to new communications for even greater impact! 

Don't miss David Schey’s conference presentation, Uplift Modeling Versus Traditional Response Modeling – Which One is Right for You?, at Predictive Analytics World San Francisco, on Tuesday, March 31, 2015, 3:55-4:40 pm.  Click here to register for attendance. 

By: Eric Siegel, Founder, Predictive Analytics World

Eric Siegel, Ph.D., founder of Predictive Analytics World and Text Analytics World, and Executive Editor of the Predictive Analytics Times, makes the how and why of predictive analytics understandable and captivating. He is the author of the bestselling, award-winning Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie, or Die, a former Columbia University professor, and a renowned speaker, educator, and leader in the field. 

No Comments yet »

December 9th 2014

Wise Practitioner – Workforce Predictive Analytics Interview Series: Carl Schleyer of 3D Results

Wise Practitioner – Workforce Predictive Analytics Interview Series: Carl Schleyer of 3D Results

By: Greta Roberts, Conference Chair, Predictive Analytics World for Workforce 2015

In anticipation of his upcoming Predictive Analytics World for Workforce conference Carl_Schleyerpresentation, Using Predictive Analytics to Create a Leadership Index, we interviewed Carl Schleyer, People Strategist & Senior Principal Consultant Workforce Analytics and Planning at 3D Results. View the Q-and-A below to see how Carl has incorporated predictive analytics into the workforce of 3D Results. Also, glimpse what’s in store for the new PAW Workforce conference.

Q:  In your work with predictive analytics, what specific areas of the workforce are you focused on, (i.e., optimizing workforce productivity, using big data to solve workforce challenges, building a workforce analytics driven culture, etc.)?

A:  My personal focus on value creation and enhancing the internal brand of HR have led to analytic work interventions across the entire employee lifecycle as well as helping Operations with scheduling and productivity optimization. 

Q:  Do you primarily work inside of HR – or inside of the Line of Business?  If Line of Business – which one(s):

A:  While I grew up in Line/Operations at a national retailer, my last 8-10 years have focused exclusively in HR Analytics.

Q:  What workforce outcomes do your models predict?

A:  Some of my favorite predictive interventions involve:

1) Staffing algorithms that proactively determine where vacancies should be posted

2) Performance reviews simplified with metrics and goals that inspire profitable employee behaviors and

3) Identification of where Leadership Risk exists within organizations (more on that later).

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

A:  Candidate preferencing.  Like it or not, our lives are becoming increasingly dependent on algorithms.  Many employers are using them to mine through the big data their Applicant Tracking Systems produce in order to prioritize applicants and recruiter workload.  If you can get a referral from an employee at your targeted company, you’ll likely more than double your chances of an interview and offer.

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

A:  I worked on an enterprise sales force effectiveness program that designed, tested, communicated, piloted, executed, and validated a data driven approach to helping field managers coach consultative sales associates. This approach leveraged targeted metrics that were tied to profitable employee behavior, and then incentivized through a new variable compensation plan.  Our first department was so successful we couldn’t convince the business to stay in pilot phase longer and after 3 months they deployed nationally.  From there we took our model to other departments and 12 months after the multi-department implementation we had generated an 8.3% improvement in productivity and an incremental $100 Million in margins.  Those were fun times and I was blessed to be surrounded by talented team members.

Q:  What is an example of surprising discoveries you have unearthed in your data?

A:  This is the hardest part of our work as there are often many layers to a problem and it can be difficult to know when to stop.  Outliers in the data often point to process or systems problems and can be interesting but time consuming to chase.  But it’s the spicy myth busting discoveries that immediately come to mind…  Once we proved that internally placed managers run more profitable stores in their first 12 months.  This finding reversed an alarming external placement trend that was nearing 50% AND changed the business focused towards developing internal bench strength.  Another politically charged discovery was around the cost of a FT employee.  Benefit costs are often managed by reducing the ratio of FT employees, but we proved that the performance differential on key financial metrics of FT versus PT employees fully offset the cost of benefits.  As a result we added FT jobs to the following year’s staffing plan instead of cutting them.

Q:  What area of the workforce do you think has seen (or will see) the greatest advances or ROI from the use of predictive analytics?

A:  Culture.  The intentional use of culture to drive business results is not done enough.  Many feel culture of an organization develops naturally and cannot be changed. However, culture is driven by specific leader and employee behaviors.  Today’s technology connects leaders with information on an unprecedented scale. Enterprise-wide data warehouses and big data analytics provide the ability to inform decisions and validate actions like never before. With this information, empowered leaders can manage performance in deeper and more meaningful ways, inspire employee behaviors and achieve desired results.  The data outcomes of those actions could then be identified, quantified and used as predictive measures that help an organization develop or maintain its desired culture. That means we should be able to build models to assess the impact of organizational or leadership changes on culture, engagement, and ultimately the bottom line.  Cultural Models would likely have executives rethinking many enterprise decisions.

Q:  Why do you think Business Leaders, HR Leaders and Analytics professionals should attend Predictive Analytics World for Workforce?

A:  This is still an emerging space.  Traditional educational degrees do not adequately prepare practitioners to do the work.  I believe that all of us are smarter than any one of us and quality conferences like PAW are the best way for us to upskill ourselves and create future standards.

Q:  Do you feel any urgency you want to pass along to your fellow HR and Business Executives to implement predictive analytics to help solve employee challenges?  Why?

A:  From a business perspective there are only two options- evolve or die.  And that extinction just might happen to the Human Resource function.  If we, as HR Analytic professionals, don’t learn how to adequately solve organizational problems, someone else from Finance, Strategy or Operations will.  

Q:  What is one misunderstanding people have about using predictive analytics to solve employee challenges?

A:  We DV 8.  That was my license plate for a while.  We deviate was meant to express that humans are complex and frequently change their minds.  They are engaged one morning, but looking at a job posting e-mail that same afternoon.  What drives and motivates someone one month/year isn’t of interest the next.  The needs of the workforce are so segmented and dynamic it’s difficult to get the degrees of precision that mathematicians, chemists, or engineers expect.

Q:  How involved has the business unit been in the work you’ve done inside of your organization?

A:  I have a somewhat controversial answer to this question.  Our work should be focused on improving the lives of our employees, the brand of our HR function and the profitability of our organizations.  This means the business unit has to be a strong partner in our work and should be actively involved with the analysis, design, testing, and deployment of our interventions.  In fact, my personal formula for success includes more involvement with the business than with my HR partners.  Just don’t tell that to the CHRO who lobbied hard to fund and grow the Workforce Analytics team.  As long as you are finding meaningful problems to solve and collaborating- you are on the right path.  The more strategic the question, the more likely we need access to information that extends beyond HR’s reach.  That means the internal owners of customer, financial, or operational data should be aware and involved in what you are doing.

Q:  SNEAK PREVIEW:  Please tell us a take-away that you will provide during your Presentation at Predictive Analytics World for Workforce.

A:  After Recruiting, my first break into the HR Generalist space was a role in Ethics.  I later had the opportunity to manage a centralized employee relations team.  It was both fascinating and scary to see what happened when the communication and collaboration between the employee and the supervisor broke down.  The process of watching over thousands of cases and seeing the negative energy and outcomes planted a question deep in my mind.  What if… What if I could detect the places where poor leadership exists?  What if I could intervene before the smoke turned to fire?  What if I could scan for management risks real-time?  What if I could identify and proactively resolve workforce conflict before it escalated?  What if I could prevent expensive employee relations scenarios from occurring?

After many focus groups, round tables, and quantitative attempts, a process I call The Digital Fingerprints of Leadership TM emerged.  At the conference I’ll present a new perspective on quantifying Leadership.  It’s a method of reimagining employee engagement, but without surveys.  Through the usage of readily available surrogate metrics you can target areas where communication, respect, and trust are breaking down.  Once identified, HR resources can be deployed, action plans can be created, and progress can be measured. 

Imagine being able to augment the once-a-year organization engagement survey? Many forward thinking companies have already realized that this snapshot in time approach to measuring the passion of their workforce is outdated and doesn’t suit their needs. The concept of leveraging existing real-time data opens the door for significant improvements to dynamically measuring action plans, retention efforts and overall business performance.

Don't miss Carl Schleyer’s conference presentation, Using Predictive Analytics to Create a Leadership Index, at PAW Workforce, on Tuesday, March 31, 2015, from 4:55-5:40 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 »

December 2nd 2014

Wise Practitioner – Predictive Analytics Interview Series: Josh Hemann of Activision

Wise Practitioner – Predictive Analytics Interview Series: Josh Hemann of Activision

By: Eric Siegel, Founder, Predictive Analytics World

In anticipation of his upcoming conference presentation, Cheating Detection in Call of Duty, at Predictive Analytics World San Francisco, March 29-April 2, 2015, we asked Josh Hemann, Principal, Game Analytics at Activision, a few questions about his work in predictive analytics.

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

A:  My team focuses on integrating analytics into large scale, operational processes for our online, multiplayer games, and mostly for the Call of Duty franchise. A lot of that work is more about optimization rather than prediction per se. But one area that is certainly prediction/classification is algorithmically detecting cheating, which can encompass a lot of different behaviors to identify in various settings. In some settings, the prediction absolutely must happen in real-time; in others, we can do batch processing and build evidence over time.

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

A:  We have various statistical models to characterize players’ engagement, their likelihood to quit playing, and even their styles. The process of fitting and testing these models teaches us a lot about how different elements of game play affect our players, which in turn helps inform design decisions for future game features. 

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

A:  In algorithmically detecting cheating the main benefit has been scale. Before using algorithms the manual review of player telemetry data could lead to at most a couple hundred cases being identified each day. Now we can act on thousands of cases per day, leading to a healthier player community while also freeing up valuable time for my colleagues to focus on other areas.

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

A: We collect a lot of telemetry when people play online, everything from where you are on a map at a particular point in time to how many shots you fired with a particular weapon. So the following is not so much a surprise as it is my constant amazement:  I only get to work with these data because there is physics code, graphics code, server code, etc. that is rendering many tens of thousands of events for each player in a single game, at 60 frames per second, and this is happening for millions of games played every day all over the world.  

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

A:  It’s easier to make predictive analytics useful when you give a lot of attention up front to the business decisions you are trying to affect and what monetary value there is in improving them.

Don't miss Josh Hemann’s conference presentation, Cheating Detection in Call of Duty, at Predictive Analytics World San Francisco, on Wednesday, April 1, 2015, from 10:00-10:20 am.  Click here to register for attendance.

By: Eric Siegel, Founder, Predictive Analytics World

Eric Siegel, Ph.D., founder of Predictive Analytics World and Text Analytics World, and Executive Editor of the Predictive Analytics Times, makes the how and why of predictive analytics understandable and captivating. He is the author of the bestselling, award-winning Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie, or Die, a former Columbia University professor, and a renowned speaker, educator, and leader in the field. 

No Comments yet »