Algorithmic Trading: XGBoost Machine Learning Model – Student Presentation

Algorithmic Trading: XGBoost Machine Learning Model

Time & Date: 12:00pm – 01:00pm , Thursday, May 7, 2026
Location: Room C-130 and via Zoom (see email and registration information), Computer Science Department, Okanagan College
Registration is open now: https://events.vtools.ieee.org/m/558962

Join us for an exciting student research presentation!
Come support and learn from students as they share their work, there will be multiple presentations happening throughout the day.
Snacks and lunch will be provided, so bring your curiosity (and your appetite)!
We’d love to see you there!

Agenda:

12:00 pm – 12:30 pm | AlgoTrade & XGBoost: Harsh
12:30 pm – 12:45 pm | AlgoTrade & XGBoost Q&A: Harsh
12:45 pm – 1:00 pm | Snacks & Refreshments

Abstract:

Stock markets generate enormous amounts of data every day, yet predicting how a stock will move throughout a trading session remains a difficult problem. This paper presents MarketSight, a system that learns from years of historical market data to forecast how individual stock prices will evolve across an entire trading day — before that day begins. By identifying patterns in past price behavior, the system produces a predicted price path for each stock, giving traders an early picture of likely intraday movement. The system runs automatically each night, updating its predictions with the latest available data. Experiments across approximately 500 US-listed stocks demonstrate meaningful forecasting accuracy, with predictions consistently outperforming naive baselines.

Speaker’s Bio:

Harsh Saw is a fourth-year Computer Science student with hands-on experience spanning software engineering and AI/ML — from writing production code to deploying real-world systems. He has worked across multiple domains in industry, building technology that goes beyond the classroom. Passionate about turning ideas into working products, Harsh enjoys the full journey from early development to live deployment. He is driven by curiosity about what technology can do when it is built to actually work in the real world.

 

 

For further information please contact: Youry Khmelevsky (email: Youry at IEEE.org)
Refreshments will be provided