MSc Thesis Defense - Computer Science: Junjun Hu

Please join the Department of Computer Science for the upcoming thesis defense:

Presenter: Junjun Hu

Thesis title: Leakage-Aware Sentiment and Multimodal Stock-Index Analysis

Abstract: Short-horizon stock-index forecasting remains difficult because returns are noisy, non-stationary, and only partly explained by historical prices and public news. This thesis investigates whether financial-news sentiment and multimodal market representations improve three-class direction classification, while asking when high accuracy reflects genuine forecasting rather than target construction. To address these questions, it develops a staged, leakage-aware experimental framework. A finance-domain language model first transforms dated headlines into lagged daily sentiment features, which are combined with market, technical, and candlestick variables in a TFT-inspired temporal classifier for five-day future returns. The study then evaluates a smoother EMA-50 trend-state task and reconstructs a published ViT–TFT–HOG design that fuses numerical sequences, candlestick images, visual descriptors, and candle geometry across multiple stock indices. Chronological splits, simple baselines, feature ablations, per-market diagnostics, and matched target controls are used throughout. The results show that sentiment is classified reliably at the text level but adds only a weak incremental signal to future-return prediction and does not yield consistent trading value. The EMA-50 task is substantially easier because its labels are smoother and more persistent. The reconstructed multimodal model achieves stable accuracy above 93% for the reported market-state task and transfers well to additional indices. However, a deterministic audit reveals that the prices defining this target are already available in the input window; when the endpoint is moved into the genuine future, performance falls close to chance. These findings show that high classification accuracy can measure state reconstruction rather than forecasting skill. The main contribution is a reproducible, target-explicit evaluation that preserves strong reconstruction results without overstating future-return predictability.


Committee Members:
Dr. Abdulsalam Yassine (supervisor, committee chair), Dr. Abedalrhman Alkhateeb, Dr. Yong Deng (Software Engineering)


Please contact grad.compsci@lakeheadu.ca for the Zoom link. Everyone is welcome.