Archive for February, 2015

February 24th 2015

Wise Practitioner – Predictive Analytics Interview Series: Bob Bress of Visible World

By: Eric Siegel, Founder, Predictive Analytics World

In anticipation of his upcoming conference presentation, TV Audience Targeting through Bob_BressPredictive Analytics at Predictive Analytics World San Francisco, March 29-April 2, 2015, we asked Bob Bress, Sr. Director, Product Management & Analytics at Visible World, a few questions about his work in predictive analytics.

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

A:  We are in the business of making television advertising inventory more valuable with applications that support the intelligent buying/selling and allocation of advertisements using advanced data and algorithms.  In doing so, we have a heavy focus on using predictive models for forecasting TV viewership patterns for specific targeted audiences.     

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

A:  We have incorporated predictive analytics algorithms in many the of our products to support decisions around maximizing advertising revenue, allocating media across a schedule, and in the automation of generating proposed media plans.

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

A:  A recent change in a TV viewership predictive model to incorporate overall trends in households watching television resulted in an 8% improvement in overall viewership forecast accuracy.

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

A:   When placing media across broad timeframes, there is some predictability to when the inventory owner will place the ads which can help in predicting overall TV viewership of advertisements.

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

A:  We can make significant improvements in how efficiently media campaigns are run on TV by improving forecasting capabilities and reacting dynamically to forecast errors.

——————–

Don't miss Bob Bress’ presentation, TV Audience Targeting through Predictive Analytics, at Predictive Analytics World San Francisco, on Wednesday, April 1, 2015 from 11:15 am to 12:00 pm.  Click here to register for attendance.

By: Eric Siegel, Founder, Predictive Analytics World

No Comments yet »

February 17th 2015

Wise Practitioner – Workforce Predictive Analytics Interview Series: Holger Mueller of Constellation Research, Inc.

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

In anticipation of his upcoming Predictive Analytics World for Workforce keynote Holger_Muellerpresentation, Why the Rapidly Changing World of Analytics Matters for both HR and Business, we interviewed Holger Mueller, Principal Analyst & VP at Constellation Research, Inc. View the Q-and-A below to see how Holger Mueller has incorporated predictive analytics into the workforce of Constellation Research. 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: I work as an industry analyst – so I help enterprises to understand the HCM and next generation application space, which includes analytics and big data. While workforce productivity is important, we have seen almost all vendors looking at ‘flight risk’ and deliver models for that scenario. The current focus is mainly on finding the right talent to fill positions both internally and externally. With the upcoming retirement and overall skills challenge, the recruiting and succession management function need all the help they can find. Another area is that both vendors and enterprises are realizing that psychographic information is key for people’s success, and are in the process of adding these capabilities to HCM decisions.

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

A: I work as an industry analyst – so neither HR or LoB. But write, speak and advise to both. Analytics give power to users in the LoB to come to their own HCM decisions – often without involving HR professionals.

Q: What workforce outcomes do your models predict?

A: As analysts we don’t have our own models, but both vendors and customers are mainly focused on recruiting at the moment.

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

A: Saving time to the business user. Once they trust their analytic software, they will go with its (recommended) decisions quickly/easily.

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: There are many success stories for analytics in HR. It would be wrong to put a few on the pedestal.

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: No specific area – certainly a few employees have seen better paycheck and retention measures based on the first wave of analytics apps that focused on ‘flight risk’. We now see a much broader use of analytics, so it cannot be associated with a single group. In the longer term the LOB user/executive will gain as more decisions can be made at greater speed and quality, which equates in time savings. What they will do with those remains to be seen.

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

A: To hear the latest state of analytics in HCM. 

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

A: Too many ‘false’ analytics are out there that do not take action or make recommendations. Many visualizations are (wrongly) called analytics.

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

A.  Understanding what real analytics are and how best practices are evolving.

Don’t miss Holger Mueller’s conference presentation, Why the Rapidly Changing World of Analytics Matters for both HR and Business, at PAW Workforce, on Tuesday, March 31, 2015, from 1:30-2:15 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 »

February 11th 2015

Q & A with Peter Morville

Peter_MorvilleBy Crystal Prag of Rising Media, Inc.

Peter is a pioneer of the fields of information architecture and user experience. His best-selling books include Information Architecture for the World Wide Web, Ambient Findability, Search Patterns and Intertwingled. He advises such clients as AT&T, Cisco, Harvard, IBM, Macy's, the Library of Congress, and the National Cancer Institute.

At Text Analytics World 2015 in San Francisco, Peter’s keynote is entitled “The Architecture of Understanding.” Catch an early glimpse of Peter’s expertise by reading the interview below and don’t forget to utilize early bird pricing now to secure your spot to learn from Peter in person at the best rate currently available.

Speaker Interview: Peter Morville, Semantic Studios

In your keynote, you talk about going deep. How do you see text analytics helping in going deep?

Peter Morville: If we hope to design better products, services, and systems, we must first understand the cultures of our users (or customers) and our stakeholders (and staff). Ethnography is one path to deep cultural insights. By observing and interviewing people in their natural habitats, we can learn a great deal about their goals, values, practices, and assumptions. Text analytics promises a different, complementary path to insight. What can we learn about the cultures of users and stakeholders by identifying their linguistic patterns and trends? By marrying high-touch ethnography and high-tech analytics, we can build towards a deeper understanding of the design elements necessary to ensure a lasting, bi-cultural fit.

In what ways do you think that text analytics has actively impacted information architecture?

Peter Morville: I’ve been interested in text analytics ever since I was in library school in the early 1990s, but I haven’t had much opportunity to use text analytics within the context of my information architecture work. I’ve worked with a few clients who use software to largely automate the process of tagging or classifying content, but most of the organizations I work with still rely on manual metadata. I’m hopeful this will change in the next few years, but only if the text analytics industry does a better job of demonstrating its value within the context of user experience. Given the growing popularity of faceted search from enterprise and ecommerce to social and mobile contexts, there’s a great opportunity to apply text analytics software to the creation and management of tags and taxonomies.

Where do you see the greatest potential for the combination of IA and text analytics?

Peter Morville: As an information architect, I’m often asked to create structural designs for massive content collections (e.g., a database of millions of scientific journal articles), so that users can find what they need. Of course, text analytics can help with findability, but I’d like to identify better ways to encourage discovery too. The intelligence community has been using text analytics to surface the “unknown unknowns” for years. Isn’t it time to leverage text analytics software to integrate findability and discovery into a wider range of applications?

What do you see as the most exciting potential for the field of IA?

Peter Morville: There are many ways to understand or define information architecture. The “polar bear book” (which we wrote in 1998) focused on organization and navigation for websites. Since then, our field has evolved to support mobile, social, and cross-channel user experiences. We are involved in planning and placemaking for ecosystems that span physical and digital contexts. This work requires that we serve as change agents and mapmakers. We help people to see differently by making the invisible visible. In today’s complex, fast-changing world, we have both an opportunity and a responsibility to serve as architects of understanding. That’s what I find most existing about the potential of the field of IA.

SNEAK PREVIEW: Please tell us a take-away that you will provide during your keynote presentation at Text Analytics World.

Peter Morville: Last September, I went hiking in the Grand Canyon, rim to rim, in a day. So, I’m walking along, thinking deep thoughts about the two thousand million year old rocks around me, when I hear a rattle. And, if you’d like to know how the story ends, and how it’s connected to everything from code to culture (and text analytics too), you’ll have to come to the keynote.

*****

Uncover what happened with Peter, the Grand Canyon, and text analytics by signing up to attend Text Analytics World. Sign up to attend by February 6th to enjoy early bird pricing.

 

No Comments yet »

February 10th 2015

How Predictive Analytics Reinvents These Six Industries

By: Eric Siegel, Ph.D., Founder, Predictive Analytics World
Originally published in Information Management

Predictive analytics is a game-changer — it's like "Moneyball" for… money. This article summarizes and links resources with late-breaking coverage of how predictive analytics reinvents six industries.

I'm going to break it to you gently. Despite all the advanced technology lining your pocket, car, home, workplace–and even the proverbial cloud floating virtually above your head–the world is a remarkably inefficient, wasteful place. The organizations that make the world go 'round, the companies, agencies, and hospitals that treat and serve us in every which way, constantly get it wrong. Marketing casts a wide net; junk mail is marketing money wasted and trees felled to print unread brochures. Institutions are blindsided by risky debtors and policyholders. Fraud goes undetected. And, critically, healthcare could use all the prognostication it can get. These are heavy costs that tax both you and I in various ways every day.

If only there were some way to run things better, to improve the effectiveness of the frontline operations that define a functional society.

Upgrading the World

Predictive analytics serves that very purpose by driving mass-scale processes empirically, guiding them with predictions generated from data. Millions of predictions a day improve decisions as to whom to call, mail, approve, test, diagnose, warn, investigate, incarcerate, set up on a date, and medicate.

In this way, predictive analytics reinvents how our world's primary functions are executed, across sectors. It boasts an intrinsic universality: A great, wide range of organizational activities can be improved with prediction–specifically, by way of predicting the behaviors and outcomes of people, the future of individual customers, debtors, patients, criminal suspects, employees, and voters. It's that generality that makes this technology so potent and ubiquitous.

Market Growth

So it comes as no surprise that predictive analytics is booming:

  • Number one on LinkedIn's "25 Hottest Skills That Got People Hired in 2014" is "statistical analysis and data mining," and number six is business intelligence. While most of the other skills listed there are forms of engineering/development (programming, etc.), the meat of the matter—the stuff of business—is what data itself tells us, rather than the infrastructures built to collect and store data.
  • Research firms project the predictive analytics market to reach $5.2 to $6.5 billion by 2018/2019 (MarketsandMarkets and Transparency Market Research).

Reinventing Industries

Prediction makes our planet rotate a bit more smoothly. Let's look at examples of this effect within six industries: Marketing, financial services, workforce management, healthcare, manufacturing, and government.

As the table of resources below reveals, a great deal of movement deploying predictive analytics is taking place within each of these industries, as enacted by various companies for various purposes—each case executed by way of predicting an outcome or behavior (e.g., click, buy, quit your job, default on a loan, or die), and using those predictions to drive operational/treatment decisions (e.g., remarket to, call, give a raise to, decline credit to, or apply a medical procedure on). Follow the links within this table to check out in detail the areas that interest you most.

Articles, videos, and events with late-breaking coverage of predictive analytics' deployment across six industries:

INDUSTRY: ARTICLES: VIDEOS ON DEMAND: EVENTS IN 2015:
Marketing predictive remarketing PAW Business Oct 14 *PAW Business (5 events)
Financial svcs
Credit risk
Insurance
Paychex, Chase
insurance study
PAW Business Oct 14
one on insurance
PAW Business (5 events)
(5 sessions on insurance)
Workforce
mgmt
Walmart
Wells Fargo
via Facebook data
talk: Talent Analytics CEO
case: call center
PAW Workforce (March)
Healthcare predictive medicine
why predict death
New book, Miner et al
PAW Healthcare 2014 PAW Healthcare (Sept)
PAW SF – March:
substance abuse
Chicago Dept Pub Health
intro training workshop
Manufacturing 4 predictive apps
big data improves mfg
predict mfg equip fail
car telematics for….
analytics in mfg PAW Manufacturing(June)
Government gov't apps—overview
IRS fraud detection
city of Chicago
disaster response
Siegel keynote (IBM) PAW Government (Oct)

 

*PAW stands for Predictive Analytics World (vendor-neutral conference series). In response to market growth, PAW has expanded to 9 annual events and has launched specialized events that focus on the specific industries listed above.

There's More: Innovative Predictive Applications

It does not stop there. Check out these other examples from the ever-widening range of industrial uses.

Recent articles covering innovative predictive applications:

… and as things warm up for the 2016 presidential election, speculation on the use of predictive analytics will emerge, given the way in which Obama for America 2012 used predictive analytics to target campaign activities.

Conclusions–The Predictive Game-Changer

As I put it to a relative over the holidays, predictive analytics is a game-changer. It's like Moneyball for… money.

As predictive analytics' adoption widens and deepens across sectors and across organizational functions, an inter-industry synergy emerges. Stories are shared between sectors–the lessons learned and proof-of-concepts viewed from neighboring industries inspire and catalyze growth. There's a cyclic effect.

And that is what the "big" in big data really means–big excitement and big impact across industries.


Some Extra Bits

Resources with which to explore advanced and emerging methods:

PA Times ImageGetting-started resources for newcomers:
The Predictive Analytics Times Executive Breakfast
The Predictive Analytics Guide
Infographic: Predictive Analytics World by the numbers

 

Eric Siegel, Ph.D. is the founder of Predictive Analytics World coming in 2015 to San Francisco, Chicago, Boston, Washington D.C., London, and Berlin the author of Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie, or Die, and executive editor of the Predictive Analytics Times. For more information about predictive analytics, see the Predictive Analytics Guide.

 

No Comments yet »

February 3rd 2015

Wise Practitioner – Predictive Analytics Interview Series: Richard Boire of Boire Filler Group

By: Eric Siegel, Founder, Predictive Analytics World

In anticipation of his upcoming conference presentation, Predicting Extreme Behavior to Richard_Boireimprove the rating structure for Travel Insurance, at Predictive Analytics World San Francisco, March 29-April 2, 2015, we asked Richard Boire, Founding Partner of Boire Filler Group a few questions about his work in predictive analytics.

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

A: Before even building a predictive analytics solution, we work with the business stakeholders to identify the exact business problem or challenge.

Once this has been identified, we then determine the behaviors that need to be optimized or minimized to solve the challenge/problem.

Our experience and breadth of work has resulted in the following type of model being built:

  • Acquisition
  • Upsell
  • Cross-sell
  • Attrition
  • Fraud
  • Credit risk
  • Claim risk

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

A: In building marketing response type models, the ROI is significantly improved as lower costs are achieved to attain the same level of revenue that would otherwise be attained without modelling.

Marketing decisions can then be made on which customers to select based on their ROI.

In building automobile claim risk predictive analytics solutions, we are predicting the loss cost of a given vehicle. By integrating this information with premium, we can then determine which vehicles are overpriced vs. those which are underpriced.

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

A: Listed below is the case of a property risk model that we built for an insurance company.

The green line represents our predicted analytics solutions while the red line represents the current premium pricing practice of the insurance company. The company’s current pricing practices are delivering value as seen by observing the area under the curve between the red line and the straight line. Yet, predictive analytics solutions built by our company are delivering even further value as depicted by the area under the curve between the green line and the redline.

graph R Boire

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

A:  In some cases, we have been able to use the data to identify a major change in someone’s life. A good example of this is identifying an individual that has just moved by observing that the address data has now changed for that individual. The ability to identify movers vs. non movers has led marketers to develop unique communication strategies towards this segment.

Another good example is tenure. We often find that customer behavior is often U-shaped with this variable which implies that newer and longer-tenured customers tend to be loyal, while the middle group or more average tenure type customers tend to be less loyal.

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

A: In building predictive risk solutions to estimate the loss amount for this travel insurance company, we encounter huge outliers that often distort or mitigate the overall impact of the model. In this particular case study, we examine an approach that allowed us to in effect produce a better model thereby reducing the impact of outlier events. The key takeaway was that we used a very pragmatic approach in solving the problem. This pragmatism enabled us to combine our domain knowledge of the business along with our data science knowledge which allowed us to arrive at a better overall solution.

Q: What has been the biggest challenge in building models over the course of your career?

A: The biggest challenge in creating predictive analytics solutions is ensuring that the target variable is created correctly. This is easier said than done as the practitioner has to do the following:

  • Identify information to be used in creating target variable
  • Creation of analytical file with pre-period where all information represents potential model variable inputs to model and post period where the only information is the actual target variable.
  • Many problems arise when information in the pre-period represents a portion of the target variable or the pre-period overlaps with the post period. These kinds of seemingly simplistic data issues represent the lion’s share of problems when it comes to overstatement of model results.

————–

Don’t miss Richard Boire’s presentation, Predicting Extreme Behavior to improve the rating structure for Travel Insurance, at Predictive Analytics World San Francisco, on April 1, 2015 from 4:40-5:00 pm. Click here to register for attendance.

Richard Boire will also be providing his new book, Data Mining for Managers: How to use Data (Big and Small) to Solve Business Challenges, to those who attend his session at PAW San Francisco. His book provides streamlined insights chock-full of engaging stories, case studies, and techniques for making the most of the masses of information and mining techniques that technology has enabled.

Enjoy his session and his book by attending PAW San Francisco.

By: Eric Siegel, Founder, Predictive Analytics World

No Comments yet »