ARCeH Externship via ExternI have some practical experience and I am focused on learning, growing skills, and finding the right career path.
A collection of practical work and projects that show my learning process, skill development, and the kinds of problems I enjoy tackling.
Processed 280K+ transactions and network-flow records with automated ETL, GMM modeling, and ML evaluation; improved fraud detection recalls by 20-25%, reduced false-positive alerts by 18%, and reduced manual review time by 35%.
Trained classification models on 60K+ MNIST images with 5-fold cross-validation, precision-recall analysis, and threshold tuning to maintain 90%+ precision while reducing false positives by approximately 18%.
I have some practical experience and I am focused on learning, growing skills, and finding the right career path.
I am Long Ta. I have some work experience but I do not yet feel like I have officially started my career. I am exploring opportunities to learn, grow my skills, and build projects that clarify the direction I want to take.
Externships
Data Analytics, Health Outcomes Externship with ARCeH
In progress
Experience
Data Engineer
3Kalo Texas Corporation · May 2025 – January 2026
Backend Developer
Suspender4Hope · May 2023 – May 2024
Education
Wichita State University, Wichita, KS
MS in Computer Science
Wichita State University, Wichita, KS
BS in Computer Science & Mathematics
Skills
Processed 280K+ transactions and network-flow records with automated ETL, GMM modeling, and ML evaluation; improved fraud detection recalls by 20-25%, reduced false-positive alerts by 18%, and reduced manual review time by 35%.
Trained classification models on 60K+ MNIST images with 5-fold cross-validation, precision-recall analysis, and threshold tuning to maintain 90%+ precision while reducing false positives by approximately 18%.
Developed VGG16, ResNet50, and EfficientNet-B0 image classification pipelines with transfer learning, augmentation, and Grad-CAM interpretability; improved validation accuracy by approximately 12%.
Built ML pipelines from network-flow features to classify benign and malicious DoH traffic, comparing Logistic Regression, Decision Trees, Random Forests, and 1-D CNN models using accuracy and confusion-matrix analysis.
✅ Verified by Extern · ⏱️ In progress
Here’s what the data says: put a pin in Bangkok. Draw a five-hour flight radius around it. You just circled half the world's population. And half of those people are kids under five, an age where survival itself isn't guaranteed. Five isn't an arbitrary number: it's the line researchers use as a proxy for a country's overall health, because almost every preventable childhood death, driven by a bad water source, poor air quality, or an infection nobody caught in time, happens before it. Clear five, and the odds of reaching adulthood jump astronomically. Don't, and the cause almost always traces back to poverty, healthcare access, environmental risk, or nutrition, something that could have been mapped, measured, and prevented in time. That's the gap this externship exists to close: turning scattered, messy public data into a specific, defensible answer about what's actually driving that risk in a given place, and pass it to the people at ARCeH who want to know about it.
The project processed public health and environmental datasets to identify factors linked to under-five mortality around a defined geographic radius. The work reviewed data limitations, applied correlational analysis methods, and documented which datasets and variables could be used to measure risk factors. The deliverables included a methodological foundation and a mapped set of candidate
I established a methodological foundation that explained what correlational data analysis can reveal, where it falls short, and which data issues commonly prevent analysis from being actionable.
