top of page

University Projects

Ongoing

Machine Learning for Monitoring Forest Restoration

For my undergraduate dissertation, I worked in collaboration with researchers from the environmental non-profit organisation Conservation International to develop a machine learning model to monitor a forest restoration project in northern Fiji using satellite imagery. My proposed machine learning model achieved 96.4% classification accuracy in identifying the presence of trees in satellite imagery and was shown to be successful to help quantitatively assess changes in forest cover between distinct time periods. My dissertation was awarded by the University of Edinburgh.

Screenshot 2021-04-18 at 18.03.33.png

Ongoing

CovidMaps: Mapping Covid-19 Data in Scotland

In May 2020, at the height of the first wave of Covid-19 in the UK, I co-developed the first data visualisation website in Scotland to help compare Covid-19 data across local authorities and health boards. The aim of the project was to provide data in a clear, simple and digestible format, allowing people to easily compare the situation across local regions in Scotland. The website has been shared widely, attaining thousands of unique viewers and the project featured in the Edinburgh University Informatics Website.

covid-scotland.png

April 2021

Predicting US Droughts with Machine Learning

Worked in a team with two other undergraduate researchers to investigate whether deep learning models - LSTMs and Transformers - could be used to predict and forecast drought conditions in the United States using meteorological data. Our results show that machine learning models can successfully be used to forecast drought conditions which are crucial for early-warning drought management systems in the US.

Screenshot 2021-04-18 at 17.51.04.png
Screenshot 2021-04-18 at 17.28.21.png

April 2021

BetterReads: Building a Book Review Search Engine

As part of my Text Technologies for Data Science coursework, I worked in a team to develop a book review search engine called BetterReads. The system searches a database of 69 million book reviews to help book lovers find new lovers depending on their review search queries. The technical system combines a sentiment analysis machine learning model with a BERT-based Transformer model to find the perfect book match depending on the users search query.

Screenshot 2021-04-18 at 17.42.11.png

March 2021

Scratch from Scratch: Online Coding Club for Kids

Lead a team of volunteers to create a 5-week online coding club for kids aged 9-11 called Scratch from Scratch. The lessons helped introduce 100+ kids across Scotland to programming for the first time. We were shortlisted for the University of Edinburgh award for Community Impact Award and the project received press coverage including being featured on British Science Week 2021.

scratch-icon.jpeg

Dec 2020

TryAI: Machine Learning for High School Students

For my Computing in the Classroom undergraduate coursework I am currently developing an AI education website for high school students aimed at ages 14-16. The goal is to create fun content that helps introduce younger learners to important concepts in data science, machine learning and AI ethics. In developing the project, I have been in contact with the former MIT Media Lab student Blakeley Payne, whose work on building a data ethics & AI education curriculum for middle school students has been a leading inspiration in developing my TryAI project.

122-1220785_robot-png-cartoon-robot-tran

Apr 2020

RemindDoor: Building a Smartlock Prototype

For the Edinburgh University System Design project I managed a team of 10 students and launched an assitive hardware product called RemindDoor. The smartlock prototype was developed with the vision of helping a diverse range users - from health carers, to Airbnb hosts. At the end of the project we pitched our prototype to investors and representatives from companies including Dyson, Amazon and Github. Our team was awarded 1st Prize in a competition with 200+ students and we won the Informatics Business Development Award for business leadership.

Lock 3.png

Dec 2019

Developing an Autonomous Drone Flight Path Game

As part of my Informatics Large Practical coursework, I was given the task to develop an autonomous drone flight system in a location-based strategy game. This project was my first time programming in Java and my software package received a top-grade, attaining 90% for my code design & implementation and 84% for my final overall report mark.

Screenshot 2019-12-27 at 12.04.17.png

Internship Projects

Sep 2020

Building a data analysis tool at Amazon Web Services

Amazon Web Services (AWS) is the world's leading cloud computing provider. I worked as a Software Development Engineer Intern in the AWS Network Performance Team, alongside world-leading engineers in the fields of computer networking, distributed computing and data center management.

For my internship, I developed a Python data analysis package to help monitor customer related network performance metrics such as throughput, latency and packet-loss. In layman's terms, I worked on a project that helped monitor cloud computing customers' speeds - e.g. how long does it take for a customer to download a Netflix video?

aws_logo_smile_1200x630.png

Sep 2019

Using Python for Investment Analysis at Generation

Generation is a top-percentile investment management comany co-founded by former US Vice President Al Gore and Goldman Sachs' Asset Management head David Blood. At Generation, got the opportunity to work in both the Global Equity Fund (c.$23bn) and Growth Equity - Sustainable Solutions Fund III (c.$1bn). 

During my internship I experimented with new data science approaches to investment analysis using online APIs and Python packages inlcuding Numpy, Pandas and Seaborn. Also, I got the opportunity to experience 

investment research, as I prepared a report on Fintech investment opportunities in Latin America and presented key findings to the fund's partners and portfolio managers.

generation-og-image (1).png

Sep 2018

Developing a machine learning banking chatbot at N26

N26 is a European mobile bank based in Berlin, Germany. They are one of the leading Fintech startups currently valued at $3.5bn and with 5million+ customers. 

At N26, I worked as a Data Science Intern where I helped build a machine learning chatbot to improve customer services. When I joined N26 the company was experiencing a period of hyper-growth. To deal with the expanding customer base, I worked in the Data Science team to build Neon - an in-house N26 customer service AI. The project was a huge success: by the time I left the chatbot could resolve 40% of customer queries in English, French and German without the need of a human.

1200px-N26_logo_2019.svg.png
bottom of page