BORONG XU

A Master's degree in Applied Computing has equipped me with a solid foundation in AI/ML, financial modeling, and data science. My expertise lies in NLP, Large Language Models (LLMs), and model validation. I am eager to apply my skills in a challenging role where I can develop and implement ML solutions, particularly in the realm of financial services and data-driven projects.

Optimized Emotion Detector with LLM, University of Toronto

• Leveraged advanced self-supervised transformers to perform audio classification tasks to detect emotions from speech.
• Fine-tuned the pretrained models using large datasets of labeled speech audio with LoRA to accelerate computation,
  demonstrating efficiency in model development and deployment.

Bidirectional Effects of Sleep and Physical Activity, University of Toronto

• Conducted statistical analysis on mobile data to explore the relationship between sleep and physical activity.
• Implemented an Autoregressive model to forecast feature values, demonstrating strong analytical and programming skills.

Parametric Model of Sneezing, University of Toronto

• Designed and implemented an LSTM model to predict facial transformations during sneezing, optimizing the model using advanced deep learning techniques.

Supply Chain Truckload Optimization, Anheuser-Busch

• Developed middleware to optimize shipment scheduling, integrating financial metrics to reduce costs by $3 million annually.
• Translated business requirements into technical solutions within a real-world financial context.

Research in Explainable AI, Washington University in St. Louis

• Researched AI planning problems and developed explainable solutions, focusing on model transparency.
• Generated human-friendly explanations for complex scheduling problems, emphasizing compliance and accuracy.

• Machine Learning in Production - DeepLearning.AI
• Deep Learning Specialization - DeepLearning.AI
• J.P. Morgan Software Engineering - JPMorgan Chase & Co.
• Lyft Back-End Engineering - Lyft, Inc.