Exploring Graph Neural Networks for Stock Market Predictions with Rolling Window Analysis

Matsunaga, Daiki; Suzumura, Toyotaro; Takahashi, Toshihiro

doi:10.48550/arxiv.1909.10660

Cited by 17 publications

(20 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• TGCN [25]: TGCN leverages a variant of graph convolutional networks [17] to propagate the historical price information on the stock graph for stock trend forecasting. It only uses historical price data and does not use the event information.…”

Section: Compared Methodsmentioning

confidence: 99%

“…Specifically, [44] proposed a new State Frequency Memory (SFM) recurrent network to discover the multi-frequency trading patterns for stock price movement prediction; [18] presented a multi-task recurrent neural network with high-order Markov random fields (MRFs) to predict stock price movement direction; [11] leveraged adversarial training to simulate the stochasticity during model training. Besides, to improve the performance of technical analysis, some recent efforts [6,12,16,25] leveraged Graph Neural Networks [17,38] to capture the relationships between different stocks.…”

Section: Technical Analysismentioning

confidence: 99%

See 1 more Smart Citation

REST: Relational Event-driven Stock Trend Forecasting

Liu

et al. 2021

Proceedings of the Web Conference 2021

View full text Add to dashboard Cite

Stock trend forecasting, aiming at predicting the stock future trends, is crucial for investors to seek maximized profits from the stock market. Many event-driven methods utilized the events extracted from news, social media, and discussion board to forecast the stock trend in recent years. However, existing event-driven methods have two main shortcomings: 1) overlooking the influence of event information differentiated by the stock-dependent properties; 2) neglecting the effect of event information from other related stocks. In this paper, we propose a relational event-driven stock trend forecasting (REST) framework, which can address the shortcoming of existing methods. To remedy the first shortcoming, we propose to model the stock context and learn the effect of event information on the stocks under different contexts. To address the second shortcoming, we construct a stock graph and design a new propagation layer to propagate the effect of event information from related stocks. The experimental studies on the real-world data demonstrate the efficiency of our REST framework. The results of investment simulation show that our framework can achieve a higher return of investment than baselines.

show abstract

Section: Compared Methodsmentioning

confidence: 99%

Section: Technical Analysismentioning

confidence: 99%

REST: Relational Event-driven Stock Trend Forecasting

Liu

et al. 2021

Proceedings of the Web Conference 2021

View full text Add to dashboard Cite

show abstract

“…Cross-stock Methods. To mine the cross-stock shared information and improve the stock trend forecasting performance, many cross-stock methods [6,13,17,27] leveraged the Graph Neural Networks [19,39] to capture the relationships between different stocks. The [6] and [13] utilize the graph convolutional networks (GCN) to capture the stocks' shareholder relations and industry relations, respectively.…”

Section: Technical Analysismentioning

confidence: 99%

“…For example, some straightforward methods [33] directly used the predefined stock concepts as input features of the linear forecasting model. In addition, some others [13,17,23,27] used the same predefined concepts to form up relations between two stocks and leveraged the Graph Neural Network (GNN), whose edges are defined by conceptual relations, to build a more accurate stock trend forecasting model. While these recent studies have revealed the potential of stock concepts in boosting stock trend forecasting, they are still enduring some limitations that restrain them from fully leveraging the value of stock concepts.…”

Section: Introductionmentioning

confidence: 99%

HIST: A Graph-based Framework for Stock Trend Forecasting via Mining Concept-Oriented Shared Information

Xu¹,

Wei-qing²,

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Stock trend forecasting, which forecasts stock prices' future trends, plays an essential role in investment. The stocks in a market can share information so that their stock prices are highly correlated. Several methods were recently proposed to mine the shared information through stock concepts (e.g., technology, Internet Retail) extracted from the Web to improve the forecasting results. However, previous work assumes the connections between stocks and concepts are stationary, and neglects the dynamic relevance between stocks and concepts, limiting the forecasting results. Moreover, existing methods overlook the invaluable shared information carried by hidden concepts, which measure stocks' commonness beyond the manually defined stock concepts. To overcome the shortcomings of previous work, we proposed a novel stock trend forecasting framework that can adequately mine the concept-oriented shared information from predefined concepts and hidden concepts. The proposed framework simultaneously utilize the stock's shared information and individual information to improve the stock trend forecasting performance. Experimental results on the real-world tasks demonstrate the efficiency of our framework on stock trend forecasting. The investment simulation shows that our framework can achieve a higher investment return than the baselines. CCS CONCEPTS• Social and professional topics → Economic impact; • Applied computing → Forecasting; • Mathematics of computing → Graph algorithms.

show abstract

“…Graph neural networks (GNNs) have recently emerged as one the most popular machine learning models for processing and analyzing graph-structured data [1,2]. GNNs have gained significant and steady attention due to their extraordinary success in solving many challenging tasks in a variety of scientific disciplines such as computational pharmacology [3], molecular chemistry [4], physics [5], finance [6,7], wireless communications [8], and combinatorial optimization [9], to name a few.…”

Section: Introductionmentioning

confidence: 99%

Graph Neural Networks with Parallel Neighborhood Aggregations for Graph Classification

Doshi¹,

Chepuri²

2021

Preprint

View full text Add to dashboard Cite

We focus on graph classification using a graph neural network (GNN) model that precomputes the node features using a bank of neighborhood aggregation graph operators arranged in parallel. These GNN models have a natural advantage of reduced training and inference time due to the precomputations but are also fundamentally different from popular GNN variants that update node features through a sequential neighborhood aggregation procedure during training. We provide theoretical conditions under which a generic GNN model with parallel neighborhood aggregations (PA-GNNs, in short) are provably as powerful as the well-known Weisfeiler-Lehman (WL) graph isomorphism test in discriminating non-isomorphic graphs. Although PA-GNN models do not have an apparent relationship with the WL test, we show that the graph embeddings obtained from these two methods are injectively related. We then propose a specialized PA-GNN model, called SPIN, which obeys the developed conditions. We demonstrate via numerical experiments that the developed model achieves state-of-the-art performance on many diverse real-world datasets while maintaining the discriminative power of the WL test and the computational advantage of preprocessing graphs before the training process.

show abstract

Exploring Graph Neural Networks for Stock Market Predictions with Rolling Window Analysis

Cited by 17 publications

References 10 publications

REST: Relational Event-driven Stock Trend Forecasting

REST: Relational Event-driven Stock Trend Forecasting

HIST: A Graph-based Framework for Stock Trend Forecasting via Mining Concept-Oriented Shared Information

Graph Neural Networks with Parallel Neighborhood Aggregations for Graph Classification

Contact Info

Product

Resources

About