What I'm Building

2026

A uOttawa capstone web app for detecting AI-generated TikTok-style videos, built around upload-based analysis, confidence scoring, and visual review.

• Lets users upload common video formats or try sample videos, then returns an AI-likelihood result with supporting evidence.
• Combines visual, motion, and source-signal checks for short-form clips that may have been compressed or re-uploaded.
• Includes review heatmaps and a manual inspection flow so users can validate model findings frame by frame.

Tools

React

Next.js

TypeScript

Python

FastAPI

Docker

Aug 2026

Enterprise-style Salesforce case management project for service, fraud, and operational risk workflows, backed by an external risk-scoring API.

• Models analyst workflows for case intake, risk assessment, evidence tracking, high-risk escalation, remediation, and reporting.
• Uses Salesforce DX source, Apex services, SOQL-backed queries, Lightning Web Components, custom objects, permission sets, and Flow automation.
• Integrates with a Python/FastAPI risk service through REST callouts and includes GitHub Actions validation for tests and code analysis.

Tools

Salesforce DX

Apex

LWC

SOQL

FastAPI

GitHub Actions

2026

A full-stack hotel booking and renting system for CSI2132, with role-based workflows for customers, employees, managers, and admins.

• Built PostgreSQL schema, constraints, triggers, indexes, seeded data, and views for hotel, room, customer, employee, booking, and renting records.
• Implemented Node.js and Express routes with EJS pages for public search, customer bookings, employee desk workflows, and admin CRUD screens.
• Added role-based login flows and access rules so each user type sees the correct operations and account-management controls.

Tools

PostgreSQL

Node.js + Express

Express

EJS

HTML5

CSS3

Sep 2023 – Nov 2023

A collaboratively built native hospital app for booking appointments, with real-time patient data sync and secure access for staff and patients.

• Developed in Java with the Android SDK to manage appointments and surface live patient updates via Firebase Realtime Database.
• Implemented authentication and role-aware access so patients and providers securely view and update visit details.
• Built CircleCI pipelines and automated tests to keep releases stable, with sprint tracking and issue workflows in Jira.

Tools

Java

Android Studio

Firebase Realtime DB

CircleCI

Jira

Sep 2022 – Dec 2022

A collaboratively built social hub for Spotify listeners to discover users with similar music taste and jump into shared playlists together.

• Collaborated on the end-to-end build so listeners could match with others who share their top artists and tracks.
• Designed a clean, approachable UI that keeps the focus on music discovery and quick connections.
• Refactored shared components and styling utilities to keep the codebase reusable, efficient, and easy to maintain.

Tools

HTML5

CSS3

JavaScript

Spotify integrations

Apr 2026

A static website mirror for the University of Ottawa Hong Kong Cultural Association, focused on club identity, events, sponsors, and student outreach.

• Introduces the association and its focus on Cantonese-speaking and Hong Kong culture in Ottawa.
• Organizes event, team, sponsor, and connection information so students can quickly understand how to get involved.
• Published through GitHub Pages with a public repository for the site source.

Tools

HTML5

CSS3

JavaScript

GitHub Pages

Jun 2026

End-to-end fraud analytics project for monitoring bank transactions, flagging suspicious activity, and supporting investigation workflows.

• Models customer, account, merchant, transaction, alert, and case-review data in PostgreSQL with dashboard-ready SQL views.
• Uses Python, Pandas, NumPy, and scikit-learn to clean data, engineer fraud-risk features, score anomalies, and export review queues.
• Documents Power BI and Excel reporting flows for fraud trends, high-risk transactions, customer risk, merchant risk, and case tracking.

Tools

Python

PostgreSQL

Pandas

scikit-learn

Power BI + DAX

Nov 2025 – Present

Auditor-facing pipeline that scores and surfaces risky general ledger journal entries, pairing anomaly detection with explainable risk factors (full report coming soon).

• Engineers journal-entry features (amount spikes, period-end timing, user frequency, approvals) and standardizes them into a model-ready dataset.
• Runs scikit-learn anomaly detection (Isolation Forest + Local Outlier Factor) to flag high-risk postings and label them with interpretable drivers.
• Exports risk tiers and supporting evidence to CSV/SQLite so auditors can triage entries quickly and trace decisions.

Tools

Python

Pandas

Power BI + DAX

SQLite

Nov 2025 – Dec 2025

Exploratory analysis of Spotify listening history to surface top artists, session patterns, and audio-feature trends, pairing export data with API lookups and reproducible notebooks.

• Aggregated raw Spotify streaming exports and enriched tracks with API audio features (energy, danceability, tempo) to create a unified plays dataset.
• Profiled listening habits by hour, weekday, and device to flag high-engagement windows and shifts in genre/artist mix over time.
• Built visual reports (heatmaps, feature distributions, cumulative play curves) and documented insights in notebooks for repeatable reruns.

Tools

Python

NumPy

Pandas

Matplotlib

MATLAB

Jupyter

Spotify APIs

Dec 2025

An executive-ready dashboard for telecom ops leaders that surfaced network health, ticket velocity, and outage hotspots.

• Modeled KPIs with DAX and built drill-through views for regional and device-level insights.
• Automated refresh pipelines so reports stayed current without manual exports.
• Packaged findings into a one-page briefing that accelerated weekly decision meetings.

Tools

Power BI + DAX

Azure Pipelines

SQL Views

Dec 2024 – Jan 2025

Valorant event analysis pipeline that pulls raw match data from VLR, shapes it into agent- and match-level CSVs, and surfaces composition and regional insights (full report coming soon).

• Pulls VLR events via vlrdevapi (e.g., Champions 2024) and turns them into agent- and match-level datasets so raw pages become structured rows you can analyze.
• Builds per-team composition summaries for every match and map, then highlights the most common comps to spot meta trends quickly.
• Rolls up region-by-region stats showing which agents and compositions get picked and how often they win, making it easy to compare regions at a glance.

Tools

Python

Pandas

vlrdevapi

SQLite