Ian Lin
Mechatronics Engineering Student at the University of Waterloo
Hi there! 👋
My name is Ian and I'm a fourth-year Mechatronics Engineering student studying at the University of Waterloo.
I'm interested in the fields of machine learning, artificial intelligence, and data science.
I'm skilled in programming with Python (pandas, matplotlib, scikit-learn, NLTK, PySpark, Keras, TensorFlow, Flask, Tkinter), C/C++, SQL, NoSQL (MongoDB), HTML/CSS, R, MATLAB. I've also used Git/GitHub, Databricks, Microsoft Azure, Microsoft Power BI, Microsoft Access, and Figma.
During my free time I enjoy going on nature walks, hitting the bike trails, listening to music, learning new technical skills, swimming, working out, drawing, and playing the cello.
Here you'll see some of my more creative work here: Design Portfolio.
Featured Projects
Finance Tracker
Defined PostgreSQL database model to gather and categorize financial transactions; implemented SQL record maintenance functions and created visual summaries to highlight key spending areas
Designed a comprehensive Power BI report using DAX measures to calculate financial metrics; generated data-driven insights and breakdowns of the user's personal finances to track income and expenses
Deployed a locally developed application using Azure App Service and Azure Database for PostgreSQL; ensured scalable and reliable cloud-based performance
View Project
TensorFlow Pneumonia Detection
Applied transfer learning on a VGG16 CNN model to detect pneumonia in chest x-ray images with 92% accuracy; enhanced model generalization and performance by implementing data augmentation on 5000+ images
Deployed TensorFlow image classification model on a web application; designed a user-focused interface to provide medical practitioners with real-time diagnostic results
View Project
Spam Message Classification
Implemented data preprocessing and feature engineering pipelines to streamline the training and evaluation of classification models using NLTK Porter Stemmer, scikit-learn TF-IDF vectorizer, and regex packages
Trained scikit-learn random forest model with grid search cross-validation to optimize hyperparameters and classify messages with 98% accuracy; developed Flask web application to identify new spam messages
View Project
Breast Cancer Diagnosis
Applied grid search cross-validation on various machine learning algorithms to fine tune hyperparameters for optimal performance; achieved 97% accuracy on an optimized Logistic Regression model
Implemented algorithm (scikit-learn random forest feature importance) to reduce the number of variables for prediction by 83%; trained Support Vector Machine model to identify malignant tumours with 96% accuracy
View Project
"Catch Them All" Turtle Simulator
Developed ROS2 nodes while applying OOP concepts to encapsulate node functionalities for controlling the main turtle movement, spawning new turtles, and capturing spawned turtles using topics and interfaces
Implemented node parameters and launch files to create a highly scalable, customizable, and organized application; reduced the number of terminal commands needed to start up the simulation by 67%
View ProjectWork Experience
Advanced Analytics Co-op
Manulife Financial Corporation
Jan 2024 - Aug 2024
- Developed scalable data pipelines to process over 200k short-term disability claims from Azure Data Lake Storage; trained XGBoost models achieving 75% recall in predicting short to long-term disability transitions
- Led progress update meetings with business team specialized in short-term disability claims; utilized SHAP to enhance model interpretability, instilling confidence in model performance and reliability
- Refactored pandas and PySpark data pipeline codebase; leveraged code profiling to eliminate bottlenecks and reduce runtime by 80%, significantly enhancing pipeline efficiency and performance
- Managed the project codebase using Git version control; collaborated with multiple developers for seamless integration and code quality maintenance, utilizing GitHub Issues to organize tasks and streamline workflow
- Designed database table architecture for storing historical short to long-term disability transition risk scores; utilized MLflow infrastructure to build a scalable model scoring pipeline for Databricks cloud-based execution
Database Analyst
Toronto Transit Commission
May 2023 - Sept 2023
- Implemented preventive measures to protect against cyberattacks by developing an encrypted password management application using Tkinter and SQL Server; stored and managed 1000+ logins for 40+ databases
- Enhanced and streamlined security management application by implementing user authentication, search, password generation, auditing, and exporting controls; developed an intuitive user friendly interface
- Configured SQL Server Agent job to upload 50+ records of email data per day; monitored and analyzed CPU usage to significantly reduce Oracle Cloud Infrastructure (OCI) costs
Machine Learning Engineering Co-op
Daily Blends
Sept 2022 - Dec 2022
- Trained scikit-learn regression models to conduct time series forecasting for assorted healthy food products at smart vending machine locations to determine optimal inventory levels that meet customer demand
- Reduced product demand forecasting time by 97% through the implementation of the developed machine learning application; streamlined company's workflow and enhanced revenue generation prospect
- Developed data pipelines by implementing pandas, NumPy, and matplotlib libraries to query and process 90+ datasets; streamlined the development of machine learning models for product demand forecasting application
Data Science Developer
Land and Resources I+IT Cluster, Ontario Public Service
Jan 2022 - Apr 2022
- Created dashboards and reports using Power BI to present insights and assist executive and partner ministry offices with operational planning in making data driven decisions
- Developed a Power BI 201 Toolkit to educate Land and Resources I+IT Cluster staff with advanced Power BI skills to enhance the efficiency and improve practices in data analytics
- Presented an automated internal interface that allowed employees to synchronize tasks with emails in organization-wide hackathon; facilitated project management processes and improved tasked management
- Achieved 2nd place in the 3rd Annual Ontario Public Service Hackathon; developed proficiency with Microsoft's low-code/no-code solutions
Jr Machine Learning Developer (WE Accelerate Program)
AltaML
Jul 2021 - Aug 2021
- Created an artificial intelligence use case to implement object tracking in real time; trained a machine learning model to track hockey players and a hockey puck to develop proficiency in Microsoft Azure
- Defined specifications based on given criteria to meet user standards; analyzed player performance and enriched the audience experience by providing critical insights about hockey player positions
- Worked collectively with AltaML and Rogers Sports and Media stakeholders to ensure timely delivery of materials; ensured full compliance of timelines using internal communication mediums via MS Teams and Zoom
Aquatics Instructor & Lifeguard
City of Markham
Mar 2019 - Mar 2020
- Tailored weekly lesson plans when teaching swimming lessons, lifesaving courses and first aid to different age divisions by guiding groups through the swimming curriculum to optimize teachings for each student
- Managed conditions of the pool by ensuring that safety regulations were met; addressed any concerns from customers to maintain professional representation of the City of Markham
- Led and conducted examinations to evaluate potential lifeguards who meet organization standards; awarded Bronze Examiner certification status from the Lifesaving Society
Education
University of Waterloo
Candidate for Bachelor of Applied Science - Mechatronics Engineering
2020-2025
Extracurricular Activities
- Introduction to Databases with MongoDB Workshop lead for Tech+ UW's Byte-Sized Conference
- Semi-Competitive Basketball Intramurals
- Semi-Competitive Ultimate Frisbee Intramurals
St Robert Catholic High School
High School Diploma
2016 - 2020
Academic Awards
- Honour Roll (2017/18/19/20)
- Highest Mark Grade 10 Music (99), Grade 11 Computer Science (100), Grade 11 Functions (100), Grade 12 Calculus and Vectors (100), Grade 12 Physics (100)
Athletic Awards
- Junior Letter Award
- Swimming MVP 2020
- Athletic Council Award
Extracurricular Activities
- Orchestra (2016-2020)
- Swim Team (2016-2020) (2016/17/18 Overall Team YRAA Swimming Champion, 2018 Boys Team YRAA Swimming Champion)
- Varsity Ultimate Frisbee (2017/18/19)
-
OFSAA Swimming (2017/18/19/20)
(2018 B-Finalist 10th-Place Jr 50m Butterfly and 2019 A-Final Finalist 4th-Place Sr 200m Medley Relay)
Certifications
AZ-900
Microsoft Certified: Azure Fundamentals
AI-900
Microsoft Certified: Azure AI Fundamentals
LinkedIn Learning Path: Getting Started with AI and Machine Learning
Gained a clear understanding of how AI and machine learning work
LinkedIn Learning Path: Become a Full-Stack Web Developer
Learned the foundations of programming for full stack developers
Udemy: ROS2 For Beginners (ROS Foxy, Humble - 2022)
Studied and applied ROS2 core concepts and tools with Python and C++
RCM Grade 6 Cello Certificate - First Class Honours
Examination Result: 83
RCM Grade 8 Cello Certificate - Honours
Examination Result: 77
RCM Grade 9 Cello Exam - First Class Honours
Examination Result: 83
RCM Advanced Rudiments Certificate - First Class Honours with Distinction
Examination Result: 100