NETpred: Network-based modeling and prediction of multiple connected market indices

Paper: arXiv 2212.05916

Authors: Alireza Jafari, Saman Haratizadeh

Abstract

Market prediction plays a major role in supporting financial decisions. An emerging approach in this domain is to use graphical modeling and analysis to for prediction of next market index fluctuations. One important question in this domain is how to construct an appropriate graphical model of the data that can be effectively used by a semi-supervised GNN to predict index fluctuations. In this paper, we introduce a framework called NETpred that generates a novel heterogeneous graph representing multiple related indices and their stocks by using several stock-stock and stock-index relation measures. It then thoroughly selects a diverse set of representative nodes that cover different parts of the state space and whose price movements are accurately predictable. By assigning initial predicted labels to such a set of nodes, NETpred makes sure that the subsequent GCN model can be successfully trained using a semi-supervised learning process. The resulting model is then used to predict the stock labels which are finally aggregated to infer the labels for all the index nodes in the graph. Our comprehensive set of experiments shows that NETpred improves the performance of the state-of-the-art baselines by 3%-5% in terms of F-score measure on different well-known data sets.

Complexity vs Empirical Score

• Math Complexity: 5.5/10
• Empirical Rigor: 6.5/10
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: NETpred presents a novel graph-based framework for index prediction using heterogeneous graph convolutional networks and semi-supervised node selection. The paper offers a solid empirical evaluation showing consistent improvements over state-of-the-art baselines, though code availability and deeper financial backtesting remain unconfirmed.

Research Flowchart

  flowchart TD
    A[Research Goal: Predict Market Index Fluctuations via Graphical Models] --> B[Data Inputs: Historical Stock & Index Price Data]
    B --> C[Step 1: Construct Heterogeneous Graph using Stock-Stock & Stock-Index Relations]
    C --> D[Step 2: Select Representative Nodes & Assign Initial Predicted Labels]
    D --> E[Step 3: Train Semi-Supervised Graph Convolutional Network GCN]
    E --> F[Step 4: Predict Stock Labels & Aggregate to Infer Index Labels]
    F --> G[Outcome: NETpred Outperforms SOTA Baselines by 3%-5% F-Score]