David Cheng | AI & ML Engineer Portfolio

About Me

I have a strong technical background in IT (14+ yrs), mostly in the fields of Network Engineering, Project Management, IT Consulting, and IT Infrastructure Management. I'm now seeking a transition into AI / ML Engineering to pursue my passion for Artificial Intelligence. In preparation for this, I've recently acquired an Introduction to Programming with Python Certificate from Harvard University (2023), a Certificate in Artifical Intelligence & Machine Learning Bootcamp from Caltech University (2025), and am constantly researching AI/ML topics or working on AI projects.

Featured Projects

Here are some highlights from my work. Visit the projects page for more details.

Sales Forecasting

Developed a model forecasting sales for 6 restaurants (10k+ records) with a 98.41% accuracy R2 and outperforming an already high naive baseline of 97.7%. Used GridSearch for hyperparameters and testing algorithms (RNNs, classical algorithms, Neural Networks), and XGBoost was chosen based on RMSE, R2, and naive baseline comparison.

Python Supervised Learning Time Series XGBoost

Learn more →

Lending Default Prediction

Developed a deep learning model predicting the % that an new client will default on a loan (10k+ records). Target data was heavily imbalanced (2.91 Mean ABS Skewness) so I mainly focused on PR-AUC and our Recall based off of F1 Optimal Threshold. Our deep learning model caught 44% of actual defaults (Recall), and PRC-AUC of 0.286 wasa 79% improvement over randomly flagging loan applicants based on our data's historical default rate of 16%--resulting in a savings of $4.1M. F1 Optimal Threshold was an aggressively low 0.19 which considered both Precision and Recall but weighed Recall more heavily so we could focus more on the minority class (defaults).

Python Supervised Learning Binary Classification Deep Learning

Learn more →

Vehicle Detection and Identification Type

Built a Convoluted Neural Network (CNN) off a ResNet50v2 backbone to detect multiple vehicles and their category type from images with an accuracy of 87% and an IoU of 88%

Convolutional Neural Network Tensorflow / Keras Resnet50v2 Transfer Learning

Learn more →

Resume

Interested in my background and experience? Download my resume to learn more about my skills, education, and professional journey.

Download Resume (PDF)

Let's Connect

I'm always open to new opportunities, collaborations, and conversations about AI and technology. Feel free to reach out!