Thoughts from the Office

THE BLOG

04
Mar

PointPredictive Launches DealerTrace

dealertrace-small

PointPredictive, Inc. today launched DealerTrace™, a comprehensive analytic solution designed to address auto-lending fraud and compliance risks. DealerTrace helps auto finance lenders manage applicant risks, including early payment default and fraud, and the risk of their dealer relationships.

Auto lending fraud occurs when information on an auto loan application is intentionally misrepresented by the borrower, a sophisticated fraud ring, or in some cases an unscrupulous dealer. When application information is manipulated, the lender may unknowingly underwrite a risky loan. Fraud presents a problem for auto lenders because loans that have misrepresentation are more likely to result in early payment default, a term lenders use to indicate when no payments are ever made on the loan.

“Our analysis and experience suggest that less than 10% of auto dealers represent the majority of the fraud and early payment default risks for auto lenders,” said Frank McKenna, Chief Fraud Strategist at PointPredictive. “DealerTrace provides auto lenders with an early warning system to identify those very few bad apples in the bunch so they can improve their overall loan quality.”

DealerTrace uses pattern recognition, a complex statistical technique that has been perfected to detect fraud based on historical data mining. The solution analyzes historical patterns of fraud, early payment default and risky dealer activity and scores each application as it comes in to the lender from a dealer. Lenders are automatically alerted when an application has a significant number of application anomalies or presents known fraud patterns. The lender can then review the application and take action before it is approved. Over time, if a particular dealer submits many applications with similar fraud patterns, the solution will alert lenders to take appropriate dealer action.

With the launch of DealerTrace, PointPredictive is forming an Automotive Lending Fraud Consortium and is encouraging lenders to share their fraud data. By pooling data at an industry level, PointPredictive can help lenders aggregate their fraud knowledge, identify new fraud patterns more quickly and in turn reduce their risk by getting in front of the fraud.

“Creating and managing a fraud consortium is a core competence for PointPredictive,” stated Tim Grace, Chairman of PointPredictive. “Members of our team used the same approach for mortgage lenders a decade ago, which resulted in reductions of 50% or more of their fraud and default losses.”

To join the Automotive Lending Fraud Consortium or to request additional information, contact [email protected]

25
Feb

Modeling Updates from PointPredictive

auto-lending

We’ve Been Busy With Some Cool New Analytic Products

We’ve been heads down busy at PointPredictive the last couple of months launching new solutions for new markets and things have been progressing nicely.

Our focus has always been to launch new analytic solutions to serve markets that need it.  In particular we’re focused on delivering analytics to both the analytics and alternative credit markets and we’ve made some significant progress on those fronts.

Automotive Lending – We’re Launching a Data Sharing Consortium and Fraud Analytic Suite

We’ve spent the last 6 months working with fraud experts, data partners and auto lenders to finalize some groundbreaking new solutions for the auto lending industry.

In particular,  PointPredictive will be launching the first ever fraud consortium for auto lenders in combination with some groundbreaking analytic products.  We’re looking to solve the problem of risk with a combination of application models and dealer risk monitoring solutions for fraud, risk and compliance.

Our release is scheduled for March 2015 so keep your eyes open for the big announcement.  Contact [email protected]

05
Nov

Making it Smart and Making Customers Happy in the Process

smallppiquote

Having just completed another successful project in record time we were thrilled when our client described our work, exactly as we would have hoped they would when we started the project. – “Point Predictive more than met our expectations..”,  “their team was available, responsive and really did an exceptional job of bringing their significant expertise to bear on our business”.  These kind words were literally music to our ears and that’s why we started PointPredictive.

Our business model has always been to partner with our customers. We bring them our expertise in data, risk and modeling and help them solve business problems quickly in a way that they can understand and use.  Through our most recent project we did just that by focusing on the business issues and working on a tactical and practical solution using smarter science.

There were many things that made this engagement successful but I felt there were 5 reasons that made it really work.

1. We started by understanding their business before we gathered the data.

There is intelligence you can derive from data but it first requires a deep understanding of the business issues to put that data into context.  That’s why we spent an entire week, working hand in hand with our customers onsite with them.  We needed to understand their business problems that they faced everyday before we could help them solve them.  After the week was over, we were able to gather years of historic data and make sense of it when we got back to the PointPredictive lab to get to work.

 2. We didn’t lock ourselves into a single analytic technique.

We realized pretty quickly on that to solve this particular issue, we were going to need to be creative and think outside of the box.  So, we decided very early on to be analytic-agnostic.  That is to say we would use any analytic technique that delivered the best predictive value while being simple enough to put into production quickly and be useable by the business.  We tried scorecards, logistic regression and even experimented with deep learning techniques.  In the end we found that a combination of techniques worked the best.

computer

3.  We scheduled regular meetings to discuss progress and raise issues.

We are big fans of iterating a solution until we get it right.  So we scheduled weekly calls with our customers to report on results of the analytics and to get their feedback through the entire process as quickly as possible.  We didn’t develop the model in a vacuum, we created the model in an iterative process hand in hand with our customer.

4. We measured model performance for them in many different ways and focused on performance.

We took great effort to deliver a full set of performance charts for our customer.  Not only did we measure the models ability to detect risk overall, but as well its ability to reduce financial risk over time.   A model that does not help reduce financial risk has a very hard time of adoption since their is no financial incentive.  We made sure that our performance charts clearly demonstrated the benefit to improve adoption of the model.

5.  We helped to operationalize the model.

The model was extremely predictive.  We were able to show that with our performance charts. That only solves half the problem however and we needed to help our customers understand how to use that model in various aspects of their business.  That’s were our business consulting backgrounds really came into play.  Having worked with over 100 lenders, banks and financial companies on analytics and risk we were able to bring our significant expertise to bear.  Operationalizing the model helped bring it to life in a way that made sense for the business to use.

It’s so great to be able to help our customers and enable them to achieve their business goals.  That makes all the hard work we do everyday worth the effort.

For questions, please contact [email protected]

30
Jun

Deep Learning Presents Exciting Opportunities to Advance Analytics for Business

One of the most exciting recent developments in the area of predictive analytics is called deep learning.  Having already advanced the state of the art in many areas such as image recognition, deep learning is now poised to deliver cutting edge results for business application clients in the real estate, mortgage, and auto lending industries.

When building a statistical model, access to quality data is key.  But few data sets in industry are fed directly into a machine learning algorithm.  Instead, the raw fields are combined and transformed to produce features, which highlight important aspects of the data and problem being addressed to a model.  Features are also a way to incorporate human business expertise into a system.

One of the challenges with features is that their creation can be time consuming, and nowadays delivering a high performing, robust system quickly is especially important.  It is also difficult to be sure if a hand created feature set fully captures the data, and using more brute-force approaches to feature creation leads to a dependence on feature selection algorithms.

Enter deep learning.  By training and stacking multiple layers of Restricted Boltzmann Machines or auto-encoder neural networks, a system can now construct its own complex internal representations or features automatically.  And these layers can be built without the need for data tags or labels, which are frequently unavailable or incomplete in big, real world data sets.  Upon the newly learned features a more typical modeling technique such as logistic regression is then used to produce the final business score.

Here at Point Predictive Inc., deep learning is one of the approaches we use to build predictive features and models more quickly.  Not only faster, the transformations learned are not typically present in hand crafted feature sets, leading to more complete models.  When coupled with solution delivery in the cloud, deep learning is helping to deliver strong model performance within short project timelines.  Can deep learning play a role in your next analytic business application?

11
Jun

5 Things that Make a Real Difference in Risk Modeling

key

Having recently completed another risk model this week, I was reflecting on some of the things that factor into building a model.  And not just a good model, but a great model that can transform the way our customers do business.

I realized that 5 things were really important.

Understand the Data – I mean REALLY understand the Data.

The biggest mistake you can make in risk modeling is not understanding each and every field in a dataset and what drives the data into it.  So many models are built in a vacuum where a scientist is not given access to the business. They review datasets without understanding how that data is used in the business operations.  When this happens, assumptions are made about the data and sometimes those assumptions are wrong.  When we build a model at PointPredictive, our scientists spend an inordinate amount of time with the client, understanding each and every data element.  It’s a painstaking process but the end result is a model that works.

Focus on the REAL problem.

In risk modeling, it is quite easy to get side-tracked and end up building a model that focuses on the wrong problem.  The advice we always give ourselves is – “follow the losses”.  If you build a risk model that reduces risk and that in turn results in reducing losses then you are solving the real problem at hand.  Focus on the REAL problem when building a model and you’ll be successful.

Iterate early and often, getting feedback from the business along the way.

Years ago, a customer conveyed to me a story of a failed project that ended up causing their business a lot of frustration.  They waited months and months for model to be delivered to them. When the final model and results were delivered it didn’t address the business problem at all and as a result was never deployed.  The fact is, great models are typically the product of lots and lots of small, incremental iterations.  After each iteration, the business provides feedback and adjustments and improvements are made.   Not only do the models improve from the frequent feedback over time but the business will end up understanding the models and that in turn will improve the odds that the model will gain acceptance.

Measure Performance of the model from every perspective that makes sense

I am not sure you can ever focus too much on model performance measurements.  As a company, we spend a lot of time working with our customers to show them how our models perform.  How much risk does the model detect?  What is the false positive of the model at each score band?  What is the number of cases created?  How will the model reduce losses over time?  These are all questions that we try to answer for customers and it makes a real difference.

Be there for Go-Live.

The first day a model is deployed is a critical one.  It’s the day that everything comes together and the end users will start to use your model.   It’s also when a lot could go wrong.  Data feeds, systems, or network connections can cause problems that impact your model. Or, in some cases,  the end users may have a problem understanding how to use the model or scores in their workflow.   Being there for Go-Live to make sure everything works according to plan is a very critical phase in the model development process.

If you look at the things that make a real difference , in risk modeling,  they are all about the same thing – bringing the business and science together.  A great model is a collaboration between operations and analytics.  The more you can bring the two together and collaborate throughout the entire modeling process, the better the end solution will be.  That’s what we believe and that’s our focus.

For questions, please contact [email protected]

19
Mar

Mortgage Fraud Technology Time!

Fraud

I was invited to speak at the MBA National Mortgage Fraud Issues Conference in Los Angeles this week and it looks to be an exceptional event – MBA Conference.

I’m always excited to speak about the future of fraud prevention, particularly when it comes to the mortgage industry. I believe this industry will be shaped by the technology that will be created over the next 2 years.

I’m celebrating my 10th year as a fraud prevention advocate for the mortgage industry and I have to say it’s been a wild ride. I started in 2004 when the word “fraud” was considered a forbidden word to even speak in public. The general consensus was that it rarely occurred and when it did it was the exception.

If you witnessed the fallout of the mortgage industry in 2007 and after, you know that this certainly was not the case and that fraud was often cited as one of the primary reasons the industry collapsed. Unfortunately, I witnessed that first-hand with the 50+ lenders I worked with over that time.

Times have changed. Fraud is front and center in the minds of lenders and they are looking to technology to help them prevent fraud in the future. Nothing makes me happier than progress.

The Way Forward

Our approach to technology is straight forward and it has always been that way. Use cutting edge technologies that have worked in more sophisticated financial services applications (such as credit cards) and then adopt and customize that technology to the mortgage industry.

When I talk about things like instant alert customization, embedded link analysis, self-learning adaptive models, dynamic workflow, and expanded customer relationship data feeds, these terms may mean very little to the mortgage industry today — but they will someday soon. I’m excited about to speak about that vision at the conference.

25
Feb

Hello Greg Gancarz!

BDS_8645

Today’s a pretty exciting day for us. Another super talented scientist, Greg Gancarz, has joined PointPredictive and he will lead our day to day analytic efforts and help us innovate for our customers.

Greg, originally from Massachusetts and an MIT and Boston University graduate, is no stranger to building advanced models on massive data sets. He’s spent the last 15 years working for analytic firms including HNC Software, FICO, and Opera Solutions building state of the art models with big data.

A key contributor to the worldwide rollout of FICO’s Falcon payment card fraud detection product, Greg has also created and delivered custom analytic solutions for clients in areas such as online banking, property insurance, and collections. Greg is named in several scientific patents for fraud, collections, and data visualization. A frequent traveler, Greg has enjoyed working with clients around the world and has often presented at user groups and conferences.

We’re thrilled to have Greg as our Principal Scientist. Greg’s expertise in neural networks and recommender systems as well as his experience leading analytic teams will be put to great use at PointPredictive as we continue to grow and develop novel analytic solutions, in the cloud, for our clients.

Welcome Aboard Greg!

20
Feb

Jim Baker Joins PointPredictive

Jim-Baker

Jim Baker is a great scientific mind. However, he is terrible at retiring. For the second time in less than a decade, Jim Baker has retired only to find himself back in another start-up.  You might question why someone would retire twice only to find themselves back in a start-up each time.  To answer that question you really have to know Jim. Jim loves to build things, to solve new problems and to help bring the San Diego Analytic community together. He has been an important mentor to many analytic scientists throughout the years.

Jim is a Pioneer in Analytics Across Multiple Industries

Tim and I started working with Jim Baker when he was at HNC Software (now FICO) managing the development of all Falcon credit and debit card models worldwide. Since Falcon protects over 2.5 billion cards across the globe, he had a tremendous responsibility and was instrumental in launching groundbreaking analytic models to the industry.

After HNC Software, Jim joined us at BasePoint Analytics and helped us launch scores of successful models and solutions in both the Mortgage and Debit industries. Jim was instrumental in helping to build and architect the cutting-edge modeling techniques that are used in those industries to this day.

It’s safe to say that the models that Jim has helped design and build are used millions of times daily whether they assess risk on credit card transactions or the likelihood of fraud on a mortgage loan.

Helping us Build a World Class Analytic Team

Our goal at PointPredictive is to build a world-class analytic capability with the smartest science and business people working together. We could think of no one better to help us make that a reality than Jim Baker. He is arguably one of the most respected and experienced Analytic minds in San Diego – which says a lot given the tremendous concentration of analytic talent here.

We are thrilled to have Jim with us (again).

03
Feb

Working with Joe

joesmall1

Tim and I first met Joe years ago when we were bringing the BasePoint Analytics fraud solution to the mortgage industry.  Joe was at Wells Fargo at the time and our analytic approach to solving mortgage fraud was quite new to the market.

To be honest, we felt that the old way of solving fraud problems by using rules-based alerts not based on scientific analysis were a thing of the past.  Being a huge proponent of analytics and science to solve business problems, Joe agreed. The rest is history. Well, not quite.

Joe has always been a believer in analytics

We ended up working with Joe on scores of projects over the years. Each time he would approach us with a new challenge, a new project to infuse analytics into every facet of operations. Each time we took on a new project with Joe we knew that it was going to be something new and cool. It helped that we shared the same fanatic enthusiasm to change the world with science. Joe is a true believer in the power of analytics; he always has been.

Serendipity and good timing

As luck would have it, Tim and I were busy researching for the next big business idea when Joe called. He wanted to start something new too. The timing could not have been better and the company took shape.

The Big Picture

Not only is Joe recognized as a pioneer in introducing analytics to the mortgage industry, he is also known as a driving force in joint ventures. For example, his work with Wells Fargo Ventures (WFV) resulted in a growth of that business to $25 billion annually.  His ability to create partnerships that make sense is something that is helping PointPredictive enter the new markets that make sense for us.

Joe’s ability to see the big picture and understand our customers is perhaps one of his biggest strengths. Having held Senior Executive positions in the corporate world, he has a sense of the real world problems that our customers face.  Not only can he get down in the nitty gritty of analytics but he can quickly help identify how those scientific techniques can help different industries thrive. We’re really lucky to be working with someone like Joe.

The Road Warrior

Perhaps the only downside for Joe is that he started up a company in Carlsbad, California, thousands of miles from Kansas City.  No worries though, he is racking up lots of frequent flyer miles as he finds himself in California nearly every week.   When he is not in California, you might find him on Skype – with Tim and I on one of our countless conference calls on any given day.

It’s great working with you Joe.

14
Jan

It’s Official – We’ve Launched

We announced our launch to the world today…”PointPredictive, Inc. launched today as a product innovator focused on providing organizations predictive science-based solutions for managing risk, providing new insight from available data and leveraging newer technology for faster deployment and enhanced user experiences. Created by entrepreneurs, executives and predictive solution veterans Tim Grace, Frank McKenna and Joe Jackson, the three PointPredictive founders address a growing market need for focused, creative, fast and results-driven expertise to design, build and deploy projects that leverage predictive science to solve today’s business challenges. Services and solutions include analytic-driven products for consumer lending, auto finance, mortgage, payment cards, real estate, and consumer rental markets.”

Check out our full press release here – Point Predictive Launch.

06
Jan

PointPredictive – Leveraging the Best of Large and Small Companies

The strength of start-up companies is that they are nimble. They do not have legacy infrastructure and integrations to slow deployment. This allows them to utilize the latest technology, smartest and newest predictive analytics and coolest user experiences.

The workforce is incredibly focused on task as they are not encumbered with administrative meetings or company wide initiatives. This allows them to be unequivocally focused on meeting customers needs and turning ideas into usable products.

Larger industry companies are uniquely positioned to own markets. They have wide distribution abilities through substantial partnerships, extensive client relationships and numerous sales channels. They have processes and infrastructure to maintain numerous product lines with large scale adoption rates.

PointPredictive brings the strength of a start-up company to the distribution positioning of a larger industry company. We bring ideas to market. We are focussed, we are fast, and we make our products smart. We focus on the clients needs and ensure success through initial product delivery. We ensure initial market adoption and then allow larger industry companies the ability to own the market by acquiring our product lines.

It’s an industry changing business model and one that will differentiate true large scale innovators.

04
Jan

PointPredictive – The Name Really Says it All.

BDS_4428

It’s time for something new. We’ve spent months analyzing, researching and planning and it’s finally here. We’re launching this week and we’re super excited about what this company represents for us.

We are PointPredictive

One of the first decisions you have to make when you start a company (which is actually pretty challenging) is to come up with a name for that company.  After thousands of names, we found one that was perfect – PointPredictive.  It just said it all to us: the approach that we would use to solve problems, the value we would provide to our customers and our fanatical belief that predictive analytics drive the most intelligent solutions.

We Help Clients Move Fast, Make it Smart

PointPredictive represents two things to us – Moving Fast and Making it Smart.  By moving fast, we mean giving our clients a team that they can rely on to get products and solutions to market quickly.  And when we say, “Make it Smart,” that’s all about delivering intelligent products that use data,  predictive sciences and state of the art technology to make that product beautifully intuitive to every person that uses it.

It’s Not Just Analytics, It’s Predictive Analytics

One reason we chose PointPredictive was to distinguish ourselves from a very popular type of analytics – Reporting Analytics.  What we do is different.  We use Predictive Analytics which relies on historic data to build models that can predict future events.  It’s an important distinction.  Predictive Analytics are forward looking, while Reporting Analytics are backward looking.  We’re all about using the past to help our clients predict what’s going to happen in the future so they can make more informed decisions.

We’re Ready to Tackle New Problems

The team at PointPredictive have worked together for many years.  When we founded BasePoint Analytics, which was later acquired by CoreLogic, we tackled the growing problem of rising Global Debit Card fraud and built predictive models that were used to score millions of transactions each day.  Then we launched the first ever Predictive Fraud Model for the mortgage industry that essentially changed the way that the industry used data and science.

It was truly groundbreaking and we are enormously proud of that accomplishment.  We don’t just talk about the awesome power of intelligent analytics.  We believe it and evangelize it in every industry and in every problem we tackle.

But it’s time for us to tackle new problems.  It’s time for us to use what we have learned from the past and apply it to the future.  Isn’t that really what Predictive Solutions are about?  I guess our name really does say it all.