AI and Omics Research Internship 2025
-
Updated
Mar 4, 2026 - R
AI and Omics Research Internship 2025
📊 Outlier toolkit for data science & ML. Detect, clean & visualize using IQR, Z-score, Mahalanobis & Isolation Forest
FastAPI for AI Engineers — Build a production-style AI Model Serving API with FastAPI. Mocked models (no GPU needed), real patterns: auth, SSE token streaming, Pydantic validation, background tasks, file uploads, global error handling. Includes a 13-step learning path, concept guide, 38 interview Q&As, and 13 passing tests.
End-to-end AI demand forecasting platform for retail supply chains using LightGBM, FastAPI, and ML pipelines.
Script for thermal boundary conductance between betta-Ga2O3 and 4H-SiC
Finds cheaper grocery substitutes and builds budget-optimized shopping carts using TF-IDF similarity and weighted preference scoring. Individual contribution to the DiscountMate capstone project.
Python analytics case study exploring customer churn drivers through data cleaning, visualization, and predictive modeling.
GPT-3.5-turbo powered marketing strategy generator for independent artists — MS Capstone, CSUEB 2026
Advanced predictive modeling workflow in R for diabetes risk assessment. Features Rubin's pooled GLM, LASSO feature selection, Youden's J statistic optimization, and thorough calibration diagnostics (Brier Score & Hosmer-Lemeshow test)
Multi-class ML model to predict football injury types (ACL, Hamstring, Lower Back, Ankle) | AdaBoost best performer | AUC: 0.85 | Synthetic data via Gretel.ai
An enterprise-grade customer churn prediction and retention analytics dashboard. Powered by an XGBoost machine learning classification pipeline, a FastAPI backend server, SQLite audit trails, and a premium cream-and-brown React single-page application containing animated Recharts panels. Dockerized and deployment-ready.
A neural network framework built from scratch with forward propagation, backpropagation, gradient descent, and real-time visualization of neurons, weights, and training.
Heart disease is one of the leading causes of death worldwide, making early prediction and prevention critically important. This project leverages machine learning (ML) techniques to analyze patient health data and predict the likelihood of heart disease.
Fully manual neural network implementation in Python using NumPy — forward pass, backpropagation, and gradient descent with no ML libraries.
To associate your repository with the machien-learning topic, visit your repo's landing page and select "manage topics."