{"ID":2823374,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.00197","arxiv_id":"2601.00197","title":"StockBot 2.0: Vanilla LSTMs Outperform Transformer-based Forecasting for Stock Prices","abstract":"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.","short_abstract":"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 atten...","url_abs":"https://arxiv.org/abs/2601.00197","url_pdf":"https://arxiv.org/pdf/2601.00197v1","authors":"[\"Shaswat Mohanty\"]","published":"2026-01-01T04:09:51Z","proceeding":"cs.CE","tasks":"[\"cs.CE\",\"cs.CL\",\"cs.LG\"]","methods":"[\"Transformer\"]","has_code":false}