
Rebecca contributed to the HWTeng-Teaching/202409-ML-FinTech repository by developing machine learning notebooks and investor-facing presentation materials over a three-month period. She built reproducible Jupyter Notebooks in Python for model comparison on financial datasets, implementing classifiers such as Logistic Regression, LDA, QDA, KNN, and Naive Bayes, and evaluated them using confusion matrices and accuracy metrics. Rebecca also created educational resources on bias-variance tradeoff, regularization, and feature selection, and managed documentation assets. Her work included XGBoost-based stock analysis and portfolio growth presentations, demonstrating depth in data analysis, financial modeling, and version control, with a focus on clarity and technical rigor.
Concise monthly summary for 2024-12 highlighting key deliverables, impact, and capabilities demonstrated across the HWTeng-Teaching/202409-ML-FinTech repository. Focused on delivering investor-facing assets and data-science materials with clear business value and technical rigor.
Concise monthly summary for 2024-12 highlighting key deliverables, impact, and capabilities demonstrated across the HWTeng-Teaching/202409-ML-FinTech repository. Focused on delivering investor-facing assets and data-science materials with clear business value and technical rigor.
Monthly summary for 2024-11: Delivered end-to-end ML/FinTech repo updates in HWTeng-Teaching/202409-ML-FinTech, focusing on model comparison for MPG prediction, educational ML notebooks and visualizations, and expanded documentation resources. No major bugs reported this month. The work enhanced experimentation velocity, learning materials, and access to reference resources for HW1111.
Monthly summary for 2024-11: Delivered end-to-end ML/FinTech repo updates in HWTeng-Teaching/202409-ML-FinTech, focusing on model comparison for MPG prediction, educational ML notebooks and visualizations, and expanded documentation resources. No major bugs reported this month. The work enhanced experimentation velocity, learning materials, and access to reference resources for HW1111.
In October 2024, delivered a reproducible ML Model Comparison Notebook for Market Direction in HWTeng-Teaching/202409-ML-FinTech. The notebook loads weekly financial data via ISLP, compares multiple classifiers (Logistic Regression, LDA, QDA, KNN, Naive Bayes), and evaluates performance with confusion matrices and accuracy metrics. It also explores KNN hyperparameters to identify an effective configuration, establishing a scalable framework for model selection and experimentation.
In October 2024, delivered a reproducible ML Model Comparison Notebook for Market Direction in HWTeng-Teaching/202409-ML-FinTech. The notebook loads weekly financial data via ISLP, compares multiple classifiers (Logistic Regression, LDA, QDA, KNN, Naive Bayes), and evaluates performance with confusion matrices and accuracy metrics. It also explores KNN hyperparameters to identify an effective configuration, establishing a scalable framework for model selection and experimentation.

Overview of all repositories you've contributed to across your timeline