January 20th 2015

Wise Practitioner – Predictive Analytics Interview Series: Mohamad Khatib of Nielsen

By: Eric Siegel, Founder, Predictive Analytics World

In anticipation of his upcoming conference presentation, Pizza Analytics & Optimization, at Mohamad_KhatibPredictive Analytics World San Francisco, March 29-April 2, 2015, we asked Mohamad Khatib, Sr. Project Manager at Nielsen, a few questions about his work in predictive analytics.

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

A: The work I have done focused on predicting customer purchases, in response to targeted advertisements and marketing promotional offerings. The aim is to help manufacturers optimize their product marketing promotional spend by predicting customer responses to different promotions.

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

A: By utilizing predictive analytics, the small business we worked with (pizza shop: manufacturer and retailer) were able to better schedule promotional campaigns that will yield the best results, and attract targeted customers.

Having informed predictions enables these pizza outlets to optimize their inventories of promoted products. In addition, they guide production staffing plans so that pizza outlet managers can schedule resources appropriately to meet the changing demands. This will help to ensure effective delivery of these products to clients.

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

A: By applying predictive analytics, the engaged pizza shops were able to effectively plan for their staffing needs, and align that with targeted promotions carried out to clients.

As predicted, one pizza shop was prepared to respond to increased demand in response to the post card promotions. As responses exceeded initial projected rates in some cases, additional staffing plans were in place to meet the increased demands and carry out the required service levels.

Also, they were able to compare effectiveness of types of promotional campaigns as applied to their targeted demographics.

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

A: Even though we utilized simplified models to provide predictive analytics, the correlation between promotional activities and client responses was easily visible and measurable. This ease of quantification of results in the pizza business produces great benefits in directing promotional activities to maximize returns on spends.

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

A: A simplified predictive analytics model can be easily developed and applied to a small business. Such limited efforts and investment will bring positive returns to manufacturers.

This simplification does not trivialize the approach, and has proven to produce valuable results and insights to predict responses to targeted pizza promotions.

In addition, it is clear that successful deployment of predictive analytics will have cross-functional impact throughout the organization. This impact applies to large as well as small organizations. Respective business processes will be impacted accordingly.

—————

Don’t miss Mohamad Khatib’s conference presentation, Pizza Analytics & Optimization, at Predictive Analytics World San Francisco, on Wednesday, April 1, 2015 from 10:25-10:45 am. Click here to register for attendance.

By: Eric Siegel, Founder, Predictive Analytics World

No Comments yet »

January 16th 2015

Wise Practitioner – Predictive Analytics Interview Series: Dominic Fortin of TD Insurance

By: Eric Siegel, Founder, Predictive Analytics World

In anticipation of his upcoming conference presentation, A Success Story: Sales and Revenue Forecasting through Predictive Analytics, at Predictive Analytics World San Francisco, March 29-April 2, 2015, we asked Dominic Fortin of TD Insurance a few questions about his work in predictive analytics.

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

A:  The models are predicting sales, cancellations, renewals for general insurance.  Units and premiums are forecasted, as well.  Twenty-three variables are predicted in 92 variances (region, product, sales channel, insurer, etc…), each level with its own specificities, creating 2,116 different models.  The models encompass all the changes to the business (rate change, new project, marketing investments). The innovation was that we were able to create generalized models without having to create 2,116 models independently.

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

A:  It allows us to not only to do our sales & revenue budget, to forecast our upcoming results but also to do scenarios on initiatives (e.g. effect of a rate change, etc…).  This capability helps the company to make sound decisions on business initiatives.

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

A:  We had models in the past based on excel, they were doing "the job" on predicting our sales & revenue.  The new models add more flexibility and rapidity and lower the risks associated with a manual excel based forecast.

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

A:  There was no real surprise.  We mastered our data well, it is more the capability to forecast at a more granular level that allows us to be more precise rather than trying to predict at high level.

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

A:  A take-away is the assistance to think about how this development method could be used to develop a large number of models for your business domain.

Don't miss Dominic Fortin’s conference presentation, A Success Story: Sales and Revenue Forecasting through Predictive Analytics, at Predictive Analytics World San Francisco, on April 1, 2015 at 3:55-4:15 pm. Click here to register for attendance.

 

By: Eric Siegel, Founder, Predictive Analytics World

No Comments yet »

January 6th 2015

Wise Practitioner – Predictive Analytics Interview Series: Pasha Roberts at Talent Analytics

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

 

In anticipation of his upcoming conference presentation, A Transaction-Based Approach to Understand Sales Representative Growth, Performance, and Gaming, at Predictive Analytics World for Workforce, we interviewed Pasha Roberts, Co-Founder and Chief Scientist at Talent Analytics Corporation. View the Q-and-A below to see how Pasha has incorporated predictive analytics into the workforce of Talent Analytics Corporation. 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?

A: We work with clients to solve workforce problems, using a data science approach to predict the ways that an employee will behave and perform. Only rarely are the problems neatly defined, but it usually comes down to estimating tenure or performance factors. We develop and deploy these models in the cloud to inform candidate selection and internal operations.

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

A: Occasionally we find an HR department that is in sync with the vast potential of predictive analytics. These people are wonderful, and are earning their place at the future of their business; several are speaking at PAW for Workforce this year. Most HR departments have not crossed this chasm; they feel that their scope is more limited.

The line-of-business tends to actually feel the actual pain, and is typically more facile with data. We often work with the Sales, Service, or Call Center Lines of Business. These operations managers are on the front line and are accountable.

Q: What workforce outcomes do your models predict?

A: We create models that predict tangible outcomes – such as dollar sales, or calls per day, or hours worked, or error rates, or tenure/survival. The business leaders decide what is important to success in a specific role, and then we build models for those factors. For example, we may model the likelihood of a job candidate to achieve a top sales level within 6 months.

I am not a big believer in working with intermediate variables, such as engagement or job satisfaction. You can’t eat engagement. People may assume that engagement drives business performance, but that link needs to be proven case by case. At that point, you might as well predict the business performance directly.

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

A: We recently deployed a model to reduce bank teller attrition at a large bank. The model predicts the Cox proportional hazard for survival in the role, based on our aptitude tool metrics.

Advisor, our deployment platform, displays the probability of a job candidate to be on the job in one year. Recruiters use this number (actually cutoff levels of this number) to move candidates forward, or not, during hiring.

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: The AUC of the attrition model above is quite good, well over 0.70, with lift over 2.0 in the important regions.

The business benefit of this is two-fold – (1) fewer bad fits, which means less wasted training due to early attrition, and (2) more good fits, which means longer employee runs and higher lifetime value. The total benefit of this incremental change will be over half a million dollars.

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

A: Cluster analysis of a recent sales assignment revealed a clear group of sales reps who were succeeding largely by cheating. They were “poaching” sales from regions assigned to other reps, pulling low-hanging fruit away from others. Reps in this cluster barely worked any hours, but had very high performance numbers.

It just goes to show that you can’t use just one KPI. And yes, we had great lift in predicting job candidates who were likely to fall into this poaching cluster.

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: The best predictive analytics can be done with largest sample sizes and quantified, quality output variables. We see the most of this in high volume roles, such as call centers, sales, retail banking, and insurance.

The costs and benefits of attrition/under-performance drive the ROI. In high volume situations, even a small increment can make millions of dollars of difference.

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

A: We need business leaders who understand what predictive analytics is, what it can do, and how to leverage the methods. It requires thinking about the world in a slightly different way, in terms of probability. This is not as hard as it may sound, and it is the key to unlocking a whole new level of corporate quality and performance.

Analytics practitioners should come to PAW for Workforce to learn – not only methods and technology, but to the sometimes-harder problem of business application and deployment. It’s the difference between solving equations and solving word problems.

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: I would like practitioners to realize the fact that there is a rare opportunity in employee analytics. Analytics can be so much more effective in hiring, because we directly choose employees, therefore predictions can directly drive results. This is a luxury that most other forms of analytics do not have – we don’t choose our customers, for example, so our ability to drive marketing results is indirect at best.

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

A: We predict patterns that tend to happen over time. We don’t predict what will happen in each specific case at each moment.

For example, if we predict that an employee has a 36% chance of staying on the job for one year; it’s still possible that they will last on the job for years. This doesn’t mean we’re wrong, because other employees with the same pattern may compensate.

As a machine learning geek, I love being “wrong” in this way, and love it more when managers disobey the models, because these variances only make new models stronger on the next iteration.

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

A: So far, very involved. The impact of our work boils down to understanding risk and tradeoffs, which is something senior managers often understand better than line managers.

You just have to speak their language, instead of going on about your latest foray into conditional random forest algorithms or how many Hadoop nodes were used.

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

A: I am working with millions of geo-located sales transactions to discover and predict patterns in how they learn to sell. It is a fascinating dataset that chronicles thousands of reps as they sink or swim, including some who cheat their way to the top. I hope to deliver insights into how employees learn, as well as techniques to analyze large unaggregated data sets.

 

Don't miss Pasha Roberts’ conference presentation, A Transaction-Based Approach to Understand Sales Representative Growth, Performance, and Gaming, at PAW Workforce, on Wednesday, April 1, 2015, from 11:15 am – 12:00 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 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 »

November 18th 2014

Wise Practitioner – Predictive Analytics Interview Series: Dean Abbott, Smarter Remarketer

Wise Practitioner – Predictive Analytics Interview Series: Dean Abbott, Smarter Remarketer

By: Eric Siegel, Founder, Predictive Analytics World
 

In anticipation of his upcoming conference keynote and workshops at Predictive Analytics World San Francisco, March 29-April 2, 2015, we asked Dean Abbott, Co-Founder and Chief Data Scientist, Smarter Remarketer, a few questions about his work in predictive analytics.

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

A: I’ve built models that predict a wide variety of behaviors and patterns. A short list is provided here:

  • Customer behavior: response, churn, product up-sell and cross-sell, best marketing creative, days to next purchase, days to next visit;
  • Signals (radar): tank, truck column of tanks; (sonar): man-made vs. biologic;
  • Financial: fraud or suspicion of fraud, debt repayment period, debt repayment amount, insurance claim repayment likelihood, claim amount of repayment.

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

A:  I’ll speak to Smarter Remarketer, Inc., the company I’m co-founder of and Chief Data Scientist. There is no one specific way our predictive models drive decisions, but they are involved in the decision-making process in several ways, all related to selecting customers to promote to, whether that be selecting customers to send an email to, show a display ad, or content on a page that is of greater interest to the customer.

Consider our models that predict the likelihood that someone will purchase a product during a visit to the company’s web site within 3 days. Each visitor is scored while they browse on the web site and at the end of their session. The company now wants to create a new campaign to increase sales of a particular product by emailing them a promotion code with a 20% discount. If the customer is likely to purchase a product on the web site within 3 days, the models will exclude these customers from the email list; why take away margin from sales that are likely to occur anyway. Or what if a customer was very likely to purchase within 7 days last week but is no longer likely this week? This is a form of churn (but based on expected behavior, not actual behavior), and these customers could be given incentives to visit again.

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

A: It is difficult to describe most of the results my models have generated because they are considered sensitive information for the company or government agency. I’ve had models in use by organizations for 10 years before they were refreshed. I’ve had another model so successful that it was put on the “do not tell” list by the organization because it became a strategic initiative for the organization. I’ve had fraud models identify multi-million dollar cases to investigate that were clearly fraud but had previously eluded detection.

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

A: Most surprising? There have been many surprises over the years, usually related to the data itself and patterns of behavior that we may overlook, but are important nevertheless. For example, with the days to next purchase models, one expects that visitors on a web site who look at lots of hot products are more likely to purchase soon; these are engaged visitors. However, it turns out that some of the most likely purchasers are those who visit just one item. The vast majority of the time, one-item visitors are not engaged and therefore are unlikely to purchase. But, if these one-item visitors were previously highly engaged, it’s a different story; they are focused like a laser beam on one product only. So the surprise was that there is this subset of visitors who look awful but are actually fantastic!

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

A: The most important take-away in my talk is this: When you prepare data for modeling, think about how the algorithms interpret the data. Each algorithm has weaknesses that can result in strange or misleading behavior. It’s our job as predictive modelers to help the algorithms do the best job they can.

Q: In addition to keynoting, you will be teaching two one-day workshops at PAW San Francisco, Supercharging Prediction with Ensemble Models and Advanced Methods Hands-on: Predictive Modeling Techniques. How would you advise attendees to choose between these workshops and would it even make sense to attend both?

A: There are many workshop options, and all of them are worthy of attending. I think of the Supercharging and Advanced Methods workshops as complementary to your Online Introduction to predictive and John Elder’s Modeling Methods, with the sequence being (1) Intro, (2) Modeling Methods, (3) Advanced Methods, and (4) Supercharging. The Modeling Methods can be taken the day before Advanced Methods in the same conference; Modeling Methods provides a framework for predictive modeling, and Advanced Methods lets you try it out on commercial software. Supercharging takes predictive modeling to the next level, introducing the methods that win modeling competitions and have provided me with extra accuracy has made the difference between successful models and very successful models in my consulting practice.

Don’t miss Dean Abbott’s keynote presentation, "The Revolution in Retail Customer Intelligence," March 31, 2015, 8:50-9:40 am,  and workshops at Predictive Analytics World San Francisco, March 29-April 2, 2015.

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 »

November 11th 2014

Wise Practitioner – Workforce Predictive Analytics Interview Series: Scott Gillespie, Managing Partner of tClara

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

 

In anticipation of his upcoming conference presentation at Predictive Analytics World for Workforce, “Using Predictive Analytics to Predict and Manage "Road Warrior" Burnout (Frequent Travelers)” Greta Roberts interviewed Scott Gillespie, Managing Partner of tClara.  View the Q-and-A below to see how Scott has incorporated predictive analytics into the workforce of tClara. 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:  The corporate road warrior – the people whose jobs require a significant amount of travel.

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

A:  Our primary stakeholder – so far – is the corporate travel manager.  We're knocking on HR's door, but find it difficult to identify the HR executive most interested in retention and employee engagement.  We're also keen to identify the LOB executives with large travel budgets.

Q:  What workforce outcomes do your models predict?

A:  We identify cohorts of travelers with high risk of burning out from their travel workloads.

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

A:  Companies can tailor their travel policies to address the needs of at-risk road warriors, such as encouraging less weekend travel, or allowing a better class of hotel.

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:  Our value prop is reducing the cost of turnover among a very valuable segment of any company's workforce.  

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

A:  We measure traveler wear and tear using a Trip Friction(R) metric.  Our data shows that turnover among frequent travelers is less related to the accumulated amount of Trip Friction, and more related to the pace and intensity of travel.

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:  As a pioneer in this niche of predicting traveler burnout, I am very keen to see companies pay attention to the predictive power of our models.  It's hard to get disparate functions, e.g. Travel, HR, Procurement and LOB Management, to collectively grasp the opportunities offered by predictive analytics.  I hope the PAW Workforce Conference helps to solve this problem.

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

A:  We'll provide benchmarks for recognizing true road warriors – those that travel more than 90% of all other travelers – and therefore, those at significant risk of traveler burnout.

Don't miss Scott Gillespie’s conference presentation, Using Predictive Analytics to Predict and Manage "Road Warrior" Burnout (Frequent Travelers), at PAW Workforce, on Tuesday, March 31, 2015, from 3:05-3:25 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 »

Next »

  • Subscribe Via Email

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

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