Student internships are just one way PAG offers bright career paths

This excerpt is part of an article that included internships at the Gene Editing Institute and Chemours Discovery Lab. It was written by Tracey Bryant and Karen Roberts and published on UD Daily on June 14, 2022. You can read the full article here.

UD’s STAR Campus shines as a place for student internships

The University of Delaware’s Science, Technology and Advanced Research (STAR) Campus is sparking joint research projects between UD and a number of companies that reside on the 272-acre site where a Chrysler auto assembly plant once stood. Clean energy, biopharmaceuticals, sustainable materials, and financial technology (fintech) are just a few areas being explored.

And that’s not all. Alongside these collaborations, student internship programs are taking shape. And that’s a big win for both the University and its students, and for companies struggling to recruit top talent in a still-hot hiring market.

“This is the toughest hiring market I’ve seen,” said David LaRoche, managing partner for U.S. operations at Predictive Analytics Group. The company is headquartered in the 10-story Tower at STAR, which USA Today highlighted in a 2019 roundup of “amazing” university and college buildings.

“But the University of Delaware is a great recruiting pool for us,” LaRoche said. “We know students come out of UD prepared, with a certain skill set and mentality to do the job.”

Business analytics on the rise at Predictive Analytics Group

Predictive Analytics Group (PAG) analyzes data in complex ways and breaks it down into easy-to-understand formats to identify key business trends and provide recommendations to improve their clients’ businesses.

A proud Blue Hen, LaRoche is a co-owner of the company with CEO Stephen Hoops and Chief Data Analytics Officer Dee Ridgeway. All three are former classmates and graduates of the Class of 1998 in UD’s Alfred Lerner College of Business and Economics. The company employs 25 people, and 40% are UD graduates, LaRoche said.

“By working with student interns 10 to 12 hours a week for a year or more, almost in a part-time employee model, we get to assess their strengths and opportunities,” LaRoche said. “But their UD education comes first. That is the priority.”

Predictive Analytics Group student internships
David LaRoche (left), managing partner at Predictive Analytics Group and a University of Delaware alumnus, works with Carson Furci, who graduated with his degree in entrepreneurship from UD this past May. Furci did a student internship with the company and is now employed there full-time as a marketing/business analyst.
David LaRoche (left), managing partner at Predictive Analytics Group and a University of Delaware alumnus, works with Carson Furci, who graduated with his degree in entrepreneurship from UD this past May. Furci did a student internship with the company and is now employed there full-time as a marketing/business analyst.

Carson Furci interned with the company over the past year and a half, working on projects ranging from developing the company website to learning the Structured Query Language (SQL) used in database management. He graduated from UD in May with his bachelor’s degree in entrepreneurship and in mid-June started working full-time at the company as a marketing/business analyst.

“There’s a lot of opportunity here, and I already feel like I’m a member of the family,” said Furci, who is from Yorktown Heights, New York. “My boss has over 25 years of experience, and my goal is to just do the best I can and to learn as much as I can. Ever since I started working for my dad in seventh grade, I’ve always enjoyed putting in the work, growing, learning and becoming proficient at something.”

In addition to offering a student internship program, PAG’s leadership team mentors students in the Horn Entrepreneurship Program, which has been ranked again among the best in the nation. The company also recently established an endowed scholarship in business analytics for UD students.


Predictive Analytics Group funds endowed scholarship

Predictive Analytics Group funds endowed scholarship at University of Delaware to engage future Business Analytics professionals

CONTACT: David LaRoche (, 302-588-7053

NEWARK, DE — As the use of data analytics expands, many executives are challenged to consolidate data from multiple legacy systems, develop in-house advanced analytics experience, and control access to specific reports across the enterprise. In many cases, they need advanced analytic support but either can’t afford them on a full-time basis or don’t know where to find them and train them.

Enter Predictive Analytics Group (PAG), a company formed by three University of Delaware alumni. PAG is poised to leverage the boom in business analytics – an industry that the U.S. Bureau of Labor Statistics predicts will grow by up to 35 percent between 2019 and 2029.

The company, which employs 25 people from offices on UD’s STAR campus – a full 40% of whom are UD grads – is adding a $50,000 endowed scholarship to its ongoing support of the UD Business Analytics department, with the first student receiving assistance in the Spring 2022 semester.

“Being able to partner with our alma mater and then sharing what we experienced as students and throughout our careers has been, and will continue to be, very rewarding for all of us at Predictive Analytics Group,” said CEO Stephen Hoops, a 1998 graduate of UD’s Business and Economics (BE) school. “We are proud to be the first company to fund a scholarship like this for the Business Analytics department and to support the next generation of top business analysts. The university is already doing a terrific job in this area as we’ve seen with the people we’ve hired and brought in as interns and contractors.”

Hoops and co-founders (and ‘98 BE classmates) Chief Data and Analytics Officer Dee Ridgway and Managing Partner of U.S. Operations David Laroche brought their own experiences in top roles at major financial institutions to their full-service management consulting company – and to emerging data analysts.

Launching the scholarship has been personally meaningful to the company leaders, especially Hoops, who originally came to UD on an athletics scholarship. When an injury abruptly changed his plans, he found himself changing majors and working at MBNA America full-time in order to graduate.

“Working full-time while I was in school made me who I am today, but it’s not something I would wish on today’s students,” Hoops said. “I’d rather students have the ability to concentrate on their school experience and it not be a secondary aspect of their life, which it was for me.”

For some time, PAG has made it a priority to support UD and its students, through philanthropy as well as sharing their expertise. The company regularly hires recent UD graduates, mentors current students through Horn Entrepreneurship programming, and offers internship positions to undergraduates. The scholarship, Hoops said, is the next step in connecting talented students with opportunities to success in the business analytics field.

“Today’s leading-edge technologies are creating new opportunities for businesses to elevate their performance through data analytics,” said Alfred Lerner College of Business & Economics Dean Bruce Weber. “We at Lerner College are delighted to see Predictive Analytics Group and our alumni step in to help advance and support our students in this rapidly growing discipline. I am grateful for PAG’s generous philanthropy and mentorship and know that, together, we can further business education opportunities for talented students.”

“Working as a part time employee for PAG under Dave LaRoche’s leadership was a great learning and development experience,” said Carson Furci, a UD senior majoring in Entrepreneurship. “I joined PAG this past Spring and started working on projects with Dave. Since day one, he has worked hard to be the best mentor and teacher to me that he can be. I have used Excel, Salesforce, Tableau, LinkedIn, and learned basic SQL coding, and was included in the redesign and enhancement of the PAG website and other social media platforms that we use. I feel the experience is invaluable and will help me in whatever role I pursue after my graduation.”

“At Predictive Analytics, we have people with a tremendous amount of experience,” LaRoche said. “It can be very tough for organizations to onboard and train new hires at once, but we can help students early in their careers, so they graduate with a foundation of skills that benefit them and make them attractive to future employers, whether it’s working with us or with someone else. But I won’t deny that the scholarship-application process is a great way to meet top candidates.”

This is especially important as the industry grows and looks for new talent. Mentorship and hands-on learning experience ensure graduates can find jobs in any number of industries, producing reports and forecasts so businesses can anticipate trends, meet customer needs, and manage their products and services better.

For Ridgeway, who works closely with the UD student interns at Predictive Analytics Group, interacting with current Blue Hens is a chance to tap into fresh talent. Students may stay with the company for several years, so Ridgeway and his colleagues also get to witness students come into their own, as they grow from undergraduate to young professional.

“Our interns are home-grown, but they have their own backgrounds and experiences, so we get insights that are different from when we were at UD in the late ’90s and early 2000s,” he said.

“The students and recent graduates that work with us are eager to learn,” Hoops added. “They want to understand your experiences and there is nothing more rewarding than being able to relay those experiences and offer them meaningful advice that will help shape their own careers.”

Banking News

A quick guided tour of analytic decision making

With the advent of AI and machine learning, some of the most complicated problems in industry have been not only understood but optimized. How can your business utilize these new techniques, and why are they so important?
First, what is machine learning and why is it important?

Machine learning is defined as “the scientific study of algorithms and statistical models to perform a specific task.” Machine learning and AI when implemented in business systems can not only automate many business processes, but also bring to light unknown patterns, predictors, and take analysis to a whole new level. Used incorrectly; overfitting models or incorrectly characterizing the problem is frequent and is something even the most talented data scientists struggle with.

First let’s go through a general overview of Machine learning techniques, then we’ll go through some examples. Machine learning can be broken into 3 main groups with multiple subsets as specified in the chart below.

Supervised learning algorithms find the relationship of variables that has the most predictive power, based on historical data. The two methods are regression and classification methods.

  • Regression-based supervised learning methods try to predict outputs based on input variables.

Unsupervised learning algorithms attempt to understand the structure of data and to identify the main drivers behind it. This is based on clustering of variables, and factor input analysis.

Deep learning uses multi-layered neural networks to analyze trends and is an attempt to artificially recreate human intelligence.

  • Deep learning is used best for unstructured large data sets. A deep learning model could use a hypothetical financial data series to estimate the probability of a stock crash, or market correction.1

Reinforcement learning encourages algorithms to explore and find the most profitable trading strategies representative of AI.

This all sounds great, but what is a relevant example? Imagine a machine is given an entire set of returns from assets and must decide which of 200 variables are dependent and independent as well as their interactions. In this case using a deep learning algorithm would be appropriate and could lead to insights our minds couldn’t come to due to the complexity of a given data set.

Let’s use some of these techniques on an applicable problem: Many Universities base their cost structure on projections of Admissions yield (matriculation rate) or the expected number of students who will accept an offer of admission for the next class. If a University is not able to accurately predict the admissions yield within a certain error range, there could be significant negative impacts to the University. This is due to high fixed costs and expected expenses for students who do not accept their offer.23

Given an easily accessible data set4 from Kaggle (a data science collaboration platform), lets run some basic algorithms to see what insights we understand in predicting Admissions yield.

Since there are over 50 other variables in this data set, let’s run a random forest classifier to see which variables have the greatest impact on admissions yield. This is a common practice to cut down convoluted data sets with many columns that are often correlated/colinear with each other.

Random forests or random decision forests are an ensemble learning method for classification, regression and other tasks that operate by constructing a multitude of decision trees at training time and outputting the class that is the mode of the classes (classification) or mean prediction (regression) of the individual trees. Random decision forests correct for decision trees’ habit of overfitting to their training set.

1Butcher, Sarah. “JPMorgan’s Massive Guide to Machine Learning Jobs in Finance.” EFinancialCareers. May 05, 2018. Accessed May 05, 2019.
2Brad, Weiner. “Can Artificial Intelligence Automate College Admissions?” Capture Higher Ed. May 02, 2019. Accessed May 05, 2019.
3Baig, Edward C. “Who’s Going to Review Your College Applications – a Committee or a Computer?” USA Today. December 03, 2018. Accessed May 05, 2019.

In this random forest there is an aggregation of 1000 decision trees; one can be seen below (cut down to a max depth of 7 nodes)

We can also use the random forest model as a predictor. Using a cross validation training split, we can train the model and test it with a subset (around 10%) of our original data set.

For 153 tests, we predict with 78% accuracy the admissions yield based upon the 23 variables we are using in the total dataset.

Before we get ahead of ourselves, let’s do some basic exploratory data analysis for each variable and see if there are any obvious correlations before we run prediction algorithms.

As we can see, the average amount of applicants hover around 5,000, and this is in comparison to the average percent admitted which hovers around 75%.

Most freshman are receiving student loans

Total instate pricing hovers around $20,000 but also goes as high as $70,000

We can also see that the average university gives 75% of freshmen grant aid, and that the average price for out of state students is around $20,000 more than in state.

Many of these relationships are to be expected but will help us understand possible correlations.

Many variables are heavily correlated and most have to do with total applicants and enrolled total, something we would assume. For admissions yield there are few variables that seem to have a high impact besides percent admitted total, which is to be expected, but there seem to be high correlations with percent of students submitting ACT scores as well as graduation rate and cost of attendance.

We can run a few Machine learning methods to see how accurately they predict Admissions yield. Let’s start out with an unsupervised learning process K-Clustering.

K-means clustering aims to partition n observations into k clusters in which each observation belongs to the cluster with the nearest mean, allowing us to understand how our data clusters as well as run further analysis.

We first need to find out the optimal number of clusters to use; we can do this given an elbow curve. This will show us the optimal score based upon the number of clusters. As we can see these plateaus around 5 clusters for some, and around 7 or 10 for others.

Now we can visualize the relationship between the two variables with a few graphs and a KNN regression to model and fit the data.

Let’s try this with a few more variables as well:

We can see the different clusters and see the red dots in the K nearest neighbors’ algorithm with the same clusters in red to predict admissions yield using both a uniform and distance method.

These predict the general trend but not as well as we would like, each one scoring around 38% accuracy. We can try a basic linear case

The linear case also seems to be accurate, although there could be a higher prediction / score
Two other methods we can try are Linear Discriminant Analysis although this gives us a poor fit.

The last models we’ll use are a few Naive Bayesian methods: Naive Bayes is a simple technique for constructing classifiers: models that assign class labels to problem instances, represented as vectors of feature values, where the class labels are drawn from some finite set. These predictions also failed to predict well.

Overall there is much information we’ve been able to obtain from this basic and general analysis with a few algorithms. There is so much more that can be done whether finding the right variables to optimize prediction capabilities, and many other variables and trends to understand and predict. But this is dependent on the timeline, budget and depth of the model needed.

Although this dataset is within the higher education hemisphere, these methods can be applied to any industry, as long as the proper checks and balances are in place. It’s important to know your data, but even more important to continue to learn new ways of interacting with it so you can obtain the best results.

Out of all the methods that we have used I would suggest using the Random forest regressor; it has the highest prediction accuracy and accounts for the large scale of this data set as well.

Using these different methods we have identified a few variables of interest that seem predictive of Admissions yield; “Applicants total”, “Percent of freshmen submitting ACT scores”, “Percent of freshmen receiving federal student loans”, “Total price for out-of-state students living on campus 2013-14”, and “Percent of freshmen receiving institutional grant aid.” Many of these variables make sense; price and aid should be highly correlated especially if the university is expensive. Next steps in this analysis would include optimizing you models, cutting down the number of variables used based upon qualitative research or expert insights.

Implementing the science of mathematics, statistics, and state of the art algorithms in order to uncover patterns and insights can reduce time and increase savings exponentially. It’s critical to understand both your data and the why behind it, as with the absence of the right models, techniques and questions, the explanatory power of the data is greatly diminished. Data analysis is incredible powerful and important; pairing the art with this science will bring your analysis to the next level, keep you on the cutting edge of the industry, ensure that your models are applicable in the real world and improve your speed to market.

If you would like to learn more about how these methods can be applied in your business, please contact Predictive Analytics Group at 844-SEEK-PAG.


COVID-19: Back to Work

Has your business been drastically effected by the COVID-19 virus? Are you unsure of how your business needs to adapt to compete? If so, check out the latest whitepaper from PAG, “Optimizing Your Business Model – COVID ERA”. Let the experienced subject matter experts at PAG explain how the COVID Era has changed consumer mindset and more importantly, how you can evlove your business to thrive now and into the future. The answers are just a click away….


News Newsletters

Credit-Card Debt in U.S. Rises to Record $930 Billion

Serious delinquencies increase, particularly among younger borrowers

WASHINGTON—Credit-card debt rose to a record in the final quarter of 2019 as Americans spent aggressively amid a strong economy and job market, and the proportion of people seriously behind on their payments increased.

Total credit-card balances increased by $46 billion to $930 billion, well above the previous peak seen before the 2008 financial crisis, according to data released by the Federal Reserve Bank of New York on Tuesday.

Some cardholders, particularly younger ones, are running into trouble.

The proportion of credit-card debt in serious delinquency, meaning payments were late by 90 days or more, rose to 5.32% in the fourth quarter, the highest level in almost eight years, from 5.16% in the third quarter. The serious-delinquency rate for borrowers from 18 to 29 years old rose to 9.36%, the highest level since the fourth quarter of 2010, from 8.91%.

Read the full article here.

News Whitepapers

The Decade When Numbers Broke Sports

In the 2010s, data and analytics changed the way games are played—for better and worse

Brad Pitt (left) played Billy Beane in ‘Moneyball,’ which was released in 2011, at the beginning of a decade that would change sports forever. PHOTO: COLUMBIA PICTURES/EVERETT COLLECTION

By Ben Cohen, Jared Diamond and Andrew Beaton

It wasn’t long ago that baseball players still bunted, football coaches were unapologetically conservative and basketball teams doubted Stephen Curry. It was only the beginning of this decade.

But what happened over the last 10 years inside MLB ballparks, NFL stadiums and NBA arenas rendered the sports almost unrecognizable. The games barely resemble the previous iterations of themselves. They have been reinvented in front of our eyes.

Read the full article here.