{"paper_id":"2411.05790","title":"Comparative Analysis of LSTM, GRU, and Transformer Models for Stock Price Prediction","authors":["Jue Xiao","Tingting Deng","Shuochen Bi"],"paper_date":"2024-10-20","paper_type":"perspective-policy","paper_url":"https://arxiv.org/pdf/2411.05790v1","page_url":"https://thequant.space/flowcharts/comparative-analysis-of-lstm-gru-and-transformer-models-fo/","scores":{"empirical_rigor":6.5,"math_complexity":5.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes to compare LSTM, GRU, and Transformer models for Tesla stock price prediction.","quote":"compares LSTM, GRU, and Transformer Models.","summary":"In recent fast-paced financial markets, investors constantly seek ways to gain an edge and make informed decisions. Although achieving perfect accuracy in stock price predictions remains elusive, artificial intelligence (AI) advancements have significantly enhanced our ability to analyze historical…","strategy":"LSTM model"},"assumptions":{"status":"available","items":[{"assumption":"The dataset has no missing values.","type":"data","stated":"explicit","quote":"the dataset covers 2,274 trading days with no missing values."},{"assumption":"Differencing the series yields a stationary series suitable for modelling.","type":"statistical","stated":"explicit","quote":"Differencing the series improved stationarity (ADF test p-value: 0.142), enhancing its suitability for modelling."},{"assumption":"LSTM is more suitable for stock time series than other models.","type":"model","stated":"explicit","quote":"From the perspective of overall indicators, the LSTM model is more suitable for stock time series"}]},"datasets":{"status":"available","items":[{"name":"Tesla stock dataset","provider":"Tesla official website","kind":"market-prices","access":"public","period":"2015-01-01 to 2024-01-16","universe":"Tesla stock","quote":"The data set used in this study comes from Tesla's official website, which covers product information, sales data, and user reviews published in multiple years."}],"known":[],"sample":{"start":null,"end":null,"market":"Tesla stock","asset_class":"equities","frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"The LSTM model achieved 94% accuracy in predicting Tesla stock price trends.","kind":"predictive-accuracy","quote":"the accuracy of the LSTM model is 94%."},{"finding":"The Transformer model achieved a fitting degree of 94.4%, which is 4.5% higher than the GRU model.","kind":"performance","quote":"the fitting degree of the Transformer model reaches 94.4%, which is 4.5% higher than that of the GRU neural network."},{"finding":"The GRU model’s MAE, MSE and RMSE values are 14.73077754, 339.9002233 and 18.43638314 respectively, indicating reduced prediction error compared to baseline.","kind":"statistical","quote":"Compared with the GRU model, the MAE value, MSE value and RMSE value are 14.73077754, 339.9002233 and 18.43638314, respectively, and the prediction error score of GRU model is significantly reduced."}],"reported_performance":{"strategy":"LSTM model","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":57,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:57:58Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}