Efficient Integration of Multi-Order Dynamics and Internal Dynamics in Stock Movement Prediction

Huynh, Thanh Trung; Nguyen, Minh Hieu; Nguyên, Thành Tâm; Nguyen, Phi Le; Weidlich, Matthias; Nguyen, Quoc Viet Hung; Aberer, Karl

doi:10.1145/3539597.3570427

Cited by 12 publications

(9 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ma et al [16] devised an attributedriven fuzzy hypergraph network to quantify the intensity of collective relationships among stocks and simulate their influence. Huynh et al [17] proposed a profit-driven framework to capture non-pairwise correlations and individual stock patterns. Song et al [18] proposed a multi-relational graph attention ranking network to capture dependencies between stocks from industry, Wiki, and price similarity relations.…”

Section: A Non-continual Graph Learning-based Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Diversified Adaptive Stock Selection Using Continual Graph Learning and Ensemble Approach

Kim,

Lee

2024

IEEE Access

View full text Add to dashboard Cite

Stock selection is essential for portfolio diversification to reduce risks and maximize profits. However, stock selection is difficult owing to the non-stationary nature of stock markets. In fact, stock markets experience abrupt or gradual concept drift because of their inherent volatility. Concept drift is a phenomenon in which the statistical characteristics of data change over time. Recent stock selection methods have adopted graph neural networks to capture the relational dependencies between stocks. These methods perform non-continual learning that uses a fixed set of stocks without knowledge retention. Noncontinual graph learning-based methods can adapt to abrupt concept drift, while continual graph learningbased methods can adapt to gradual concept drift because they involve knowledge retention. To adapt to both abrupt and gradual concept drifts, we propose a stock selection framework called DASS, which combines non-continual and continual models for diversified adaptation. For both models, we employ graph learning to extract both temporal and relational dependencies. Our graph learning method relies on three main components: (1) low-level temporal modeling, which extracts temporal dependencies of individual stocks, (2) relational modeling, which extracts relational dependencies between stocks, and (3) high-level temporal modeling, which extracts temporal dependencies from the learned relational dependencies. Furthermore, DASS constructs simple graphs and hypergraphs based on dynamic time warping of stock prices and volume data. The performance of DASS is compared with that of state-of-the-art stock selection methods. Experimental results for stocks included in the Standard & Poor's 500 index reveal that DASS achieves a compounded annual growth rate of 83.2%, outperforming the second-best method by 23.0%P.

show abstract

Section: A Non-continual Graph Learning-based Methodsmentioning

confidence: 99%

“…To consider both abrupt and gradual concept drifts, a diversified approach is necessary rather than relying on an approach to handle either abrupt or gradual concept drift. tion methods, those in [8], [12], [17] employ the walkforward testing method [20] to account for diverse market volatilities, as illustrated in Fig. 1.…”

Section: Introductionmentioning

confidence: 99%

Diversified Adaptive Stock Selection Using Continual Graph Learning and Ensemble Approach

Kim,

Lee

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The predefined relationships greatly limited the types of relationships among stocks markets which are highly volatile, as shown in Figure 1. Therefore, many studies in recent years started to construct dynamic hidden stock relationships to adapt to highly volatile market, such as hidden conceptual relationships (Xu et al 2021a), potential relationships among stocks and sectors (Hsu, Tsai, and Li 2021), similarity based dynamic hidden relationships (Wang et al 2022), relevance implicit hypergraph relations (Huynh et al 2023), etc.…”

Section: Spatio-temporal Based Stock Selectionmentioning

confidence: 99%

CI-STHPAN: Pre-trained Attention Network for Stock Selection with Channel-Independent Spatio-Temporal Hypergraph

Xia,

Ao,

et al. 2024

AAAI

View full text Add to dashboard Cite

Quantitative stock selection is one of the most challenging FinTech tasks due to the non-stationary dynamics and complex market dependencies. Existing studies rely on channel mixing methods, exacerbating the issue of distribution shift in financial time series. Additionally, complex model structures they build make it difficult to handle very long sequences. Furthermore, most of them are based on predefined stock relationships thus making it difficult to capture the dynamic and highly volatile stock markets. To address the above issues, in this paper, we propose Channel-Independent based Spatio-Temporal Hypergraph Pre-trained Attention Networks (CI-STHPAN), a two-stage framework for stock selection, involving Transformer and HGAT based stock time series self-supervised pre-training and stock-ranking based downstream task fine-tuning. We calculate the similarity of stock time series of different channel in dynamic intervals based on Dynamic Time Warping (DTW), and further construct channel-independent stock dynamic hypergraph based on the similarity. Experiments with NASDAQ and NYSE markets data over five years show that our framework outperforms SOTA approaches in terms of investment return ratio (IRR) and Sharpe ratio (SR). Additionally, we find that even without introducing graph information, self-supervised learning based on the vanilla Transformer Encoder also surpasses SOTA results. Notable improvements are gained on the NYSE market. It is mainly attributed to the improvement of fine-tuning approach on Information Coefficient (IC) and Information Ratio based IC (ICIR), indicating that the fine-tuning method enhances the accuracy and stability of the model prediction.

show abstract

“…Second, MLP-based mixing over stocks essentially performs information exchange among stocks based on the learned weight matrix. As pointed out in the previous works (Sawhney et al 2021;Huynh et al 2023), stock correlations are complex, and the direct stock-to-stock mixing may compromise the model performance. For instance, two stocks in the same industry may randomly have similar trends or divergent trends over time.…”

Section: Introductionmentioning

confidence: 98%

“…STHAN-R (Sawhney et al 2021) augments the corporate relevance based on Wiki data and uses hypergraph convolution to propagate higher-order neighbor's information. The latest method ESTIMATE (Huynh et al 2023) also uses hypergraph to capture the non-pairwise correlations with temporal generative filters for individual patterns per stock.…”

Section: Introductionmentioning

confidence: 99%

StockMixer: A Simple Yet Strong MLP-Based Architecture for Stock Price Forecasting

Fan,

Shen

2024

AAAI

View full text Add to dashboard Cite

Stock price forecasting is a fundamental yet challenging task in quantitative investment. Various researchers have developed a combination of neural network models (e.g., RNNs, GNNs, Transformers) for capturing complex indicator, temporal and stock correlations of the stock data.While complex architectures are highly expressive, they are often difficult to optimize and the performances are often compromised by the limited stock data. In this paper, we propose a simple MLP-based architecture named StockMixer which is easy to optimize and enjoys strong predictive performance. StockMixer performs indicator mixing, followed by time mixing, and finally stock mixing. Unlike the standard MLP-based mixing, we devise the time mixing to exchange multi-scale time patch information and realize the stock mixing by exploiting stock-to-market and market-to-stock influences explicitly. Extensive experiments on real stock benchmarks demonstrate our proposed StockMixer outperforms various state-of-the-art forecasting methods with a notable margin while reducing memory usage and runtime cost.Code is available at https://github.com/SJTU-Quant/StockMixer.

show abstract

Efficient Integration of Multi-Order Dynamics and Internal Dynamics in Stock Movement Prediction

Cited by 12 publications

References 24 publications

Diversified Adaptive Stock Selection Using Continual Graph Learning and Ensemble Approach

Diversified Adaptive Stock Selection Using Continual Graph Learning and Ensemble Approach

CI-STHPAN: Pre-trained Attention Network for Stock Selection with Channel-Independent Spatio-Temporal Hypergraph

StockMixer: A Simple Yet Strong MLP-Based Architecture for Stock Price Forecasting

Contact Info

Product

Resources

About