Accurate forecasting of financial markets remains a long-standing challenge due to complex temporal and often latent dependencies, non-linear dynamics, and high volatility. Building on our earlier recurrent neural network framework, we present an enhanced StockBot architecture that systematically evaluates modern attention-based, convolutional, and recurrent time-series forecasting models within a unified experimental setting. While attention-based and transformer-inspired models offer increased modeling flexibility, extensive empirical evaluation reveals that a carefully constructed vanilla LSTM consistently achieves superior predictive accuracy and more stable buy/sell decision-making when trained under a common set of default hyperparameters. These results highlight the robustness and data efficiency of recurrent sequence models for financial time-series forecasting, particularly in the absence of extensive hyperparameter tuning or the availability of sufficient data when discretized to single-day intervals. Additionally, these results underscore the importance of architectural inductive bias in data-limited market prediction tasks.

翻译：金融市场预测因复杂的时间依赖性（通常为潜在依赖）、非线性动态和高波动性而长期面临挑战。基于我们早期的循环神经网络框架，本文提出了一种增强的StockBot架构，该架构在统一的实验设置下系统评估了基于注意力机制、卷积和循环的现代时间序列预测模型。尽管基于注意力和受Transformer启发的模型提供了更高的建模灵活性，但广泛的实证评估表明，在采用一组通用的默认超参数进行训练时，精心构建的标准LSTM模型始终能实现更优的预测精度和更稳定的买入/卖出决策。这些结果凸显了循环序列模型在金融时间序列预测中的鲁棒性和数据效率，尤其是在缺乏广泛超参数调优或数据量不足（当数据离散化为单日间隔时）的情况下。此外，这些结果强调了架构归纳偏置在数据受限的市场预测任务中的重要性。