Toronto, ON • jacealloway@gmail.com • 289 382 9279 • LinkedIn • GitHub
Jace Alloway

Jace Alloway

Welcome to my portfolio. I am a machine learning engineer and data scientist with a strong background in physics, mathematics, and software engineering from the University of Toronto. I build advanced technical solutions, scalable systems, and machine learning models for complicated business use cases.

Please consider the full breadth of my skills, experience, and my list of projects and coursework below.

View Projects Explore Coursework Teaching Resources

About Me

Having grown up in Dundas, Ontario, I moved to Toronto in 2020 to pursue my BSc. in physics and mathematics at the University of Toronto. Having over 5 years of technical experience in problem solving, programming, critical thinking, and in research environments, I combine strong analytical thinking with technical execution. The full breadth of my skills include advanced theoretical and applied mathematics, classical and quantum statistical mechanics, field theory, chaos dynamics, general relativity, scientific methods and research, advanced computational modeling and machine learning, development of business solutions and use cases, and backend data pipeline software development.

Research

  • Data mining, data interpretation
  • Scientific computing, numerical methods, discrete mathematics
  • Methodology design, algorithm development, research communication

Business Assets

  • Tableau
  • Microsoft Power Automate
  • Microsoft Lists
  • Microscoft Excel
  • Google Sheets
  • Communication to stakeholders
  • Project management, documentation, and reporting

Education

  • BSc. Physics and Mathematics, University of Toronto (2020-2025) Academic History
  • High School Diploma, Dundas District High School (2016-2020)

Software Development

  • Python
  • SQL (Postgres, MySQL)
  • TypeScript/Javascript
  • Bash/Zsh
  • Git/Github
  • Azure Databricks
  • Google Cloud Platform
  • Digital Ocean
  • Fortran
  • Perl
  • LaTeX
  • Apache Spark
  • Fico Decision Modeler (DRL)
  • CSS, HTML
  • Conda, Spyder, VSCode
  • Jupyter Notebooks
  • Microsoft Power Automate, Microsoft Lists API

Leadership

  • Highly teachable
  • Problem solving, critical thinking
  • Strong communication skills, both written and verbal
  • Teamwork, collaboration, and interpersonal skills
  • Time management, organization, and project management skills
  • Adaptability, resilience, and a strong work ethic in fast-paced environments
  • Managing teams, delegating tasks, providing mentorship, and fostering a positive work environment

Python Libraries

  • Pandas, Numpy, SciPy
  • Requests, FastAPI
  • Matplotlib, Seaborn
  • Keras, TensorFlow, Pytorch, Sci-Kit Learn, XGBoost
  • Datetime, OS, Sys, Logging
  • Selenium
  • Google-Client-API, Mailgun API
  • Pygame
  • SymPy
  • Gradio
  • Librosa, Soundfile, Pydub
  • dbutils, SQLAlchemy

Mathematics and Physics

  • Advanced calculus (single/multi-variable to n-dimensions, vector analysis, complex analysis, variational)
  • Linear algebra (abstract vector spaces, SVD, eigenvectors, matrix decompositions, Jordan canonical forms)
  • Probability and statistics (generalized distributions, hypothesis testing, regression)
  • Numerical methods (root finding, integration, differential equations, interpolation)
  • Optimization (convex optimization, gradient descent, Lagrange multipliers)
  • Approximation methods (series solutions, Taylor expansions)
  • Differential equations (ordinary and partial, partial wave decomposition, Green's functions)
  • Tensor calculus, differential geometry (geodesics, manifold metrics)
  • Transformation methods (Fourier, Laplace, Z-transforms)
  • Advanced classical methods (Lagrangian and Hamiltonian mechanics, chaos theory, nonlinear dynamics, thermodynamics)
  • Advanced quantum mechanics (angular momentum and spin, perturbation theory (TDPT, TIPT, degenerate), quantum field theory (QED, QCD, electroweak unification), scattering theory, Feynman diagrams, statistical physics, particle physics)
  • General relativity (Einstein field equations, Schwarzschild and Kerr metrics, black hole physics)
  • Relativistic electrodynamics (Maxwell's equations, gauge invariance, radiation)
  • Computational physics (finite difference methods, finite element methods, Monte Carlo simulations, molecular dynamics, Quantum ESPRESSO, GEOS-Chem)
  • Many-body quantum field theory (thermal field theory, path integrals, renormalization group, Bloch states, self-energy, BCS theory)

Machine Learning

  • Generalized linear models (logistic regression, linear regression with L1-L2 regularization)
  • Convolutional Neural Networks (softmax, ReLU, convolutional layers, pooling layers, batch normalization, dropout)
  • Recurrent Neural Networks (LSTM, GRU)
  • Decision trees, random forests, gradient boosting (XGBoost)
  • Model evaluation metrics (ROC curves, PR curves, confusion matrices, PSI bins)
  • Feature engineering (hyperparameter tuning, dimensionality reduction, selection)
  • Model lifecycle management (data preprocessing, model training, validation, deployment, monitoring)
  • Explainability analysis (SHAP values, feature importance, partial dependency plots)
  • Time series analysis (segmented augmentation, spectral analysis)
  • K-Folds cross-validation, bootstrapping, resampling
  • Linear discriminant analysis, principal component analysis, clustering (K-means, hierarchical), Silhouette score

Professional Experience

Data Scientist II The Toronto-Dominion Bank. July 2025 - Current

Work within the TD Bank Canadian Fraud Performance Management team to develop and deploy machine learning models for fraud detection. Develop GLMs (Logistics, Linear regression with L1-L2 regularization) and XGBoost models, assess feature development and selection across a broad range of variables, and compute performance metrics such as ROC, PR curves, and PSI bins generation. Write fully-automated API-integrated code to generate monthly model performance reports and dashboards for internal stakeholders for over 50 models, reporting on key metrics such as fraud rates, transaction volumes, and model accuracy.
Work closely with TD stakeholders to onboard vendor models (Visa, Fico, etc.), write model developent reports, issue compliance documentation for the Compliance Oversight of Models Office (COMO), and ensure all models meet regulatory requirements. Transition in-house models between TD databases, including overriding feature engineering, validating and testing model scores, and constructing and deploying rules. Fully automate processes within TD's data analytics platform (Azure Databricks) using Apache Spark, SQL, and Python. Maintain and monitor all team scripts within Github, document processes within Confluence/JIRA, and work closely with TD's internal fraud teams to meet business needs. Build TypeScript automations for internal team dashboarding via Microsoft Power Automate and the Microsoft Lists API.

Data Engineer C3 Toronto Global. September 2024 - Current

Work with a small team to design an advanced ETL pipeline for processing and transforming large-scale data from the Planning Center Online website. Generate API keys and manage integrations via REST APIs to pull and process data. POST processed data through the GCP (Google API) and automate dashboarding via Google sheets. Utilize data tools such as Digital Ocean Droplets and GCP to program an Ubuntu server to execute the pipeline on a daily basis, auto-email status reports to team members (Mailgun API), and ensure the system is fully automated and robust.
Currently in it's preliminary stages, future endeavours for this project involve time series neural network constructions, linear regressive predictive modeling, implementation of an LLM for front-end querying, and white-listed dashboard engineering.

Climate Model Researcher (Internship) UofT, Atmospheric Physics Computational Modeling Group. April 2024 - September 2024

Investigate the consequences of a new regridding technique for the GEOS-Chem chemical transport model developed by Harvard University. This regridding technique involved evaluating fine-grid tracer flow concentrations through model timesteps for Carbon (CO) and implementing a mathematical divergence algorithm to transform the grid structure from a vector structure to a scalar structure. Regridding can be easily performed over a scalar field, from which gradients were taken to reveal underlying transport dynamics at the new resolution.
This project involved managing multi-facted NetCDF NASA-GMAO assimilated data and processing model outputs using Python, Perl, and Fortran. This project was conducted on a UofT supercomputing cluster (Ubuntu - Bash server). Findings are included in contribution to a publication currently in-review under the supervision of Dr. Dylan Jones.

Teaching Assistant UofT, Department of Mathematics. September 2023 - April 2025

Assist in the instruction of the second-year calculus course MAT235, Multivariable Calculus, for the University of Toronto's Department of Mathematics. Responsibilities include leading multiple weekly tutorial sessions, grading assignments and exams, and providing support to students in understanding course material during office hours. Develop strong communication and teaching skills while working closely with students and faculty members to ensure a positive learning experience. Invigilate exams and issue weekly problems taken up in class.

Customer Experience Associate The Toronto-Dominion Bank. September 2023 - July 2025

Work as a customer representative at the Toronto-Dominion Bank, providing high-quality service to customers, resolving inquiries, and assisting with various banking needs. Develop strong communication and problem-solving skills while working in a fast-paced environment. Manage cash flow, resolve customer requests, analzye risk. Collaborate with team members to ensure customer satisfaction and contribute to the overall success of the branch. Provide advice to customers to meet financial needs including overdraft protection and credit cards. Fiscal 2024 TD Legends runner-up and quality 'high' rating. Complete audit and adhere to internal regulations and compliance standards.

Cook, Sous Chef Various locations. May 2018 - April 2023

Work as a line cook and sous chef at various restaurants in the Greater Toronto Area. Develop strong teamwork, time management, and cooking skills while working in a high-pressure environment. Prepare and cook food according to recipes and quality standards, manage inventory and supplies, and ensure a clean and safe work environment. Collaborate with team members to ensure efficient kitchen operations and contribute to the overall success of the restaurant. Notable locations include: Shy's Place Restaurant, Copetown Woods Golf Course and Bistro, Bar Centrale di Terroni, La Bettola di Terroni.