An unsupervised graph-based network visualization of the news providing insight into what is being reported and how it is interconnected, featured by Neo4j. Graphs+ allows for visualizing bias and the differences in coverage between news sources. The project is composed of 3 parts. A scalable crawler collecting a corpus of 250k articles for Doc2Vec ML model training. A pipeline for processing articles including generating document embeddings, knowledge enrichment with DBpedia + ConceptNet, and community detection on an article similarity graph.
React.js web app for generating lyrics in the style of over 40 artists, getting about 20,000 unique visitors a month. The lyrics are composed using an LSTM to predict the rhyming pattern of lyrics generated by a Markov Model.
Google Assistant Action for exploring the latest news stories, developed for DANAMIC creative agency. The voice assistant makes recommendations for more content and explaining how the articles are relevant by using the underlying knowledge graph. The Google Action showcases some features that can be used to create voice experiences for news and media sites. The content reccomendation engine was deployed as a scalable API using the serverless framework and the Google Action was developed using the Node.js (Jovo) framework.
An XGBoost model for predicting an astronaut’s physical activity based on their biometric data, automating the manual task of logging. The project was selected as a national finalist in the Canadian Space Agency Challenge.
I love building things and solving technical challenges. At Shopify, I'm working on new products to help merchants. Previously at IMRSV, I worked on performant speech to speech translation models for edge devices.
I'm currently interested in information retrieval, fintech, and graph databases.
Get In Touch
More than anything, I like meeting people and having interesting conversations. If you want to have a chat about anything, from information retrieval to space exploration, feel free to reach out!