At BAIG, we combine the depth of academic research with the agility of real-world application, delivering AI strategies that resonate with today's business landscape.
Fine Tuning Models
Adobe Atlas revolutionizes the research landscape by empowering scholars with the tools to dynamically design studies centered around PDF content.
This project was an incredible learning experience, and allowed me to work with various different parts of the AI tech stack
Web development, CMS
Lofi Bytes: AI-Generated Lofi Music Web App
FamilyFund is a crowdfunding platform for friends and family. Allowing users to take personal loans from their network without a traditional financial institution.
We developed a custom CMS to power their blog with and optimised their site to rank higher for the keywords “Gary Vee” and “Tony Robbins”.
Working with Studio, we felt more like a partner than a customer. They really resonated with our mission to change the way people convince their parents to cash out their pensions.
NLP Modeling & Research
EU Parliament Text Sentiment Analysis
Optimized a text classification scheme to assess the presence of Euroskepticism in 3,000+ EU parliamentary texts by developing a sentiment analysis machine learning model with Keras and Scikit-learn, backed by the USE (Universal Sentence Encoder).
Uplifted sentiment prediction accuracies by 70% by using imbalanced-learn oversampling to normalize skewed training data.
Exploring the intersection of machine learning and political science research was an exciting experience. The project really showcased how interdisciplinary the applications of natural language processing are.