About
As AI systems increasingly stand in for human respondents in research, they raise the hard question of whether we can trust what they produce, and whether they carry hidden biases. My research answers that by building autonomous AI agents that generate synthetic respondents and complete surveys, then rigorously measuring how faithfully they reflect real populations.
Alongside the academic work, I’ve partnered with Delta, Blue Cross Blue Shield of TN, Atlanticus, and Southern Company on applied machine learning, and presented at INFORMS and JSM. I’m a builder at heart, and I love playing with data.
Education
Bowling Green State University
University of Nigeria
Publications
Industry Research
addimages/delta.jpg
Delta Air Lines
Customer ExperienceAnalyzed over 32M calls, 13M messages, and 60M intent records to reduce repeat customer contacts. A CatBoost model reached 77% accuracy and drove a modeled 13% reduction.
addimages/southern.jpg
Southern Company
Churn ForecastingForecast early customer churn across 64 engineered features. A random forest reached 96% accuracy and 96% F1.
1st place · CDSA Industry CompetitionBlue Cross Blue Shield of TN
HealthcareEvaluated continuous glucose monitoring across over 500K member records and claims, with case-control matching on 7,500 pairs. Type I patients on CGM saw significantly greater HbA1c reductions than matched controls.
Atlanticus
Credit RiskModeled credit risk on about 1M records, applying SMOTE for class imbalance and trimming 458 features to 116. A random forest reached 88% accuracy and 81% precision.
3rd place · CDSA Industry CompetitionSelected Data Science Projects
SMS Spam Detection
Five classifiers across 5,574 text messages. Random forest reached 98.1% accuracy.
GitHubAnimal Image Classification
Transfer learning with MobileNetV2 and Bayesian hyperparameter tuning on 1,200 images, reaching 90%.
GitHubCredit Card Fraud Detection
Five classifiers on European cardholder data. A neural network reached 96% accuracy.
GitHubFraud Detection at Scale
A PSOAANN one-class model built on Spark, running over 10M+ transaction records.
GitHubAmazon Coupon Recommender
A coupon-usage recommender built from ensemble and boosting classifiers with competitive accuracy.
GitHubU.S. Flight Delay Analysis
Longitudinal multilevel models across 29 major airports. ORD and ATL topped 5,000 delay hours.
GitHubSelected Talks
addimages/informs.jpg
Bridging the Gap: COSTAR-A for Smarter Prompting in Localized Language Models
addimages/jsm.jpg
Optimizing Credit Risk Classification Using Machine Learning Techniques
Teaching
Over a decade teaching mathematics, statistics, and data science across the U.S. and Nigeria, as both instructor of record and teaching assistant. Roles marked IoR were taught as instructor of record.
| Course | Level | Role & Term |
|---|---|---|
| Introduction to Data Science DATA 1501 | Bachelor's | IoR Spring 2026 · TA Fall 2023 |
| Python for Data Science DS 7140 | Master's | TA · Spring 2025 |
| Statistical Computing STAT 7020 | Master's | TA · Fall 2023, Spring 2024 |
| Data Mining in Business Analytics STAT 4440 | Bachelor's | TA · Spring 2022 |
| Data Mining STAT 6440 | Master's | TA · Spring 2022 |
| Regression Analysis STAT 5020 | Bachelor's, Master's | TA · Fall 2021 |
| Linear and Integer Programming OR 6610 | Master's | TA · Fall 2021 |
| Elementary Differential Equations I & II MTH 203 / 204 | Bachelor's | IoR 2019–2021 |
| Elementary Mathematics I & II MTH 101 / 102 | Bachelor's | IoR 2019–2021 |
Honors
addimages/award.jpg
Outstanding Student Award
Top doctoral student in the PhD in Data Science & Analytics, Kennesaw State University.
addimages/award3mt.jpg
Three Minute Thesis — First Place
Graduate College, Kennesaw State University.
James A. Sullivan Outstanding Graduate Student Award
A $400 award to the top graduate student in the M.S. in Applied Statistics program at BGSU.