GRAPH CNN PRED : A STOCK MARKET INDICES PREDICTION USING A GRAPH BASED DEEP LEARNING SYSTEM

Battle Count: 378

The paper presents a novel approach combining graph neural networks and CNNs for stock market prediction, showing improved performance over baseline models and potential for trading applications.

Requires implementation of both graph neural networks and CNNs, as well as data preprocessing and graph construction based on feature correlations.

The paper provides details on the model architecture and data preparation, but lacks specific hyperparameters and full implementation details.