Researchgnnquant financetechnical indicatorsmultivariate time series
Graph Model Improves Short-Term Stock Forecasting
|
5.9
A new paper proposes a graph neural network framework for short-term stock trend prediction, modeling sliding 5-day windows as dynamic graphs and incorporating MA5 and RSI14 technical indicators. Reported experiments show the method achieves 61.2% accuracy and 65.3% F1, outperforming machine-learning baselines and indicating graph-based models capture short-term trading signals more effectively.
Scoring Rationale
Method shows measurable improvement and practical signals, but limited novelty and single-source reporting reduce overall impact.
Practice interview problems based on real data
1,500+ SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
