Paper Reading | NGAT: Long-Term Stock Prediction with Graph Attention Networks

Paper link: arxiv.org/pdf/2507.0201... Code link: github.com/FreddieNIU/N... Graph representation learning methods have been widely applied in the financial domain, enhancing company representations through inter-firm relationships. However, existing approaches face three major challenges: (1) the advantages of relational information are constrained by downstream task design; (2) graph models specifically designed for stock prediction often suffer from poor generalizability due to high computational complexity; and (3) empirically constructed firm relationship graphs lack effective comparative evaluation across different graph structures. To address these issues, this paper proposes a long-term stock prediction task and develops NGAT—a node-level Graph Attention Network tailored for firm relationship graphs—while experimentally demonstrating the limitations of existing graph comparison methods that rely solely on downstream task performance. Experimental results on two datasets consistently validate the effectiveness of both the proposed task and model. 1 Background Graph Neural Networks (GNNs) learn context-aware embeddings reflecting graph structure via message-passing mechanisms that aggregate neighborhood node features, making them the mainstream approach in graph representation learning. This success has driven their application in stock prediction—modeling firms as nodes and inter-firm relationships as edges to capture momentum spillover effects. Existing studies typically follow a paradigm of “constructing firm relationship graphs → applying GNNs to aggregate node embeddings → evaluating on downstream tasks”, yet face the following challenges: Limitations of short-term prediction: Most existing work focuses on next-day trend prediction (a one-day forecasting horizon), failing to fully exploit the GNN’s capability to capture long-term momentum spillover (which may span multiple days); Insufficient model adaptability: General-purpose GNNs (e.g., GCN, GAT) assume homogeneous node feature distributions, whereas nodes (firms) in firm relationship graphs exhibit distinct behavioral patterns, rendering shared attention mechanisms inappropriate; Lack of graph construction evaluation: Firm relationship graphs are built empirically, with no effective method for comparing the quality of different graph structures based on downstream task performance. 2 Problem Definition This paper aims to address the following core problems: 1. Modeling long-term momentum spillover: Existing short-term predictions (e.g., next-day) cannot adequately leverage the lagged effect of inter-firm momentum spillover (potentially spanning multiple days) and ignore volatility—a key risk indicator; 2. Adaptation to firm relationship graphs: Shared attention mechanisms in general-purpose GNNs are unsuitable for firm relationship graphs where nodes (companies) exhibit heterogeneous feature distributions; 3. Evaluation of graph construction methods: There is a lack of effective methods to compare graph structural quality based on downstream task performance. 3 Method 3.1 Task Definition: Long-Term Stock Prediction Return Mean Prediction: Predict whether the average return over the next T trading days exceeds that over the previous T trading days. The label is defined as where is the log-return of stock s on day d, and p_{d}^{s} denotes the adjusted closing price. Labels are categorized into four scenarios: Surge (LP, N+, positive return in the prior period followed by higher returns), Rebound (LN, N+, negative return in the prior period followed by positive returns), Pullback (LP, N−, positive return in the prior period followed by negative returns), and Crash (LN, N−, negative return in the prior period followed by even lower returns). Volatility Prediction: Predict the standard deviation of returns over the next T trading days, defined as 3.2 Model Architecture: NGAT

NP-DNN: A DNN-Based Stock Market Price Prediction Method Outperforming LLMs with 99.21% Accuracy

Original article: mp.weixin.qq.com/s/Twgh... Stock price prediction is an important yet challenging topic in economics due to market randomness. Conventional statistical time-series forecasting methods often fail to effectively predict the probabilistic range of future stock prices. This paper proposes NP-DNN for stock price prediction, employing z-score normalization to standardize stock price data and using an MLP to learn complex nonlinear relationships among stock market prices. Compared with other methods incorporating large language models (LLMs), NP-DNN achieves an accuracy of 99.21%. Abstract Stock market price prediction is a significant interdisciplinary research area relying on the intersection of finance, statistics, and economics. Conventional statistical time-series forecasting methods often fail to effectively predict the probabilistic range of future stock prices. This paper proposes NP-DNN for stock price prediction, employing z-score normalization to standardize stock price data and using an MLP to learn complex nonlinear relationships among stock market prices. Compared with other methods incorporating large language models (LLMs), NP-DNN achieves an accuracy of 99.21%. Introduction Stock price prediction is an important yet challenging topic in economics due to market randomness. Prior to investment, data analysis is essential; massive stock price data significantly influence investment decisions, and stock price fluctuations are affected by factors such as supply and demand. Existing methods struggle to cope with complex market dynamics, whereas AI, machine learning (ML), and deep learning (DL) techniques can capture intricate relationships and yield superior predictions. This study predicts stock prices through the following components: · Neural Prophet captures historical patterns and handles irregularly spaced time series, thereby improving the quality of inputs fed into the DNN. · Deep Neural Networks (DNNs) learn complex nonlinear relationships to achieve accurate price predictions. · Multi-Layer Perceptron (MLP) performs feature extraction to enhance prediction performance and provide higher-quality inputs for the DNN. Methodology This study employs NP-DNN to predict stock prices based on extracted features and Optuna-based hyperparameter optimization. Using the Crunchbase dataset as input, preprocessing techniques—including z-score normalization and missing-value imputation—are applied to ensure model consistency. The MLP learns underlying patterns to generate feature representations. Figure 1 illustrates the stock price prediction process. Dataset The Crunchbase dataset is a publicly available database containing accessible LinkedIn profile data. The platform provides business and professional information for both public and private enterprises. Experiments were conducted on this dataset in September 2021. Data are categorized into three types: organizations, people, and investments; additionally, the dataset includes samples of companies that have LinkedIn profiles listed on Crunchbase. Preprocessing Preprocessing Crunchbase data enhances the quality of raw numerical data and improves the accuracy and value of financial information. Z-score standardization is applied to normalize the data, facilitating the identification of financial statistical regularities and patterns, and supporting analyses such as stock market prediction. A two-stage approach addresses data irregularity: first, outliers are removed using pandas-based techniques; second, temporal interpolation is performed via linear interpolation to estimate missing values between data points.

Pentair plc. (PNR) Stock Forecasts

1 day ago

Morningstar released an analyst report on Pentair plc., stating channel inventory adjustments set the stage for a pool rebound in 2027. The report analyzed segments including pool, water technologies, and flow.

Yahoo Finance Singapore

Pentair plc. (PNR) Stock Forecasts

Yahoo Finance Singapore

2026-06-10

Ecolab Inc. Insider Trading Activity

2026-06-10

Ecolab Co-COO Sells Shares Worth Over $2.6M

2026-06-11

Ecolab Director Purchases 7,750 Shares in Open-Market Transaction

2026-06-12

Michel Doukeris Purchases Shares of Ecolab Inc (ECL)