{"paper_id":"2410.01843","title":"Optimizing Time Series Forecasting: A Comparative Study of Adam and Nesterov Accelerated Gradient on LSTM and GRU networks Using Stock Market data","authors":["Ahmad Makinde"],"paper_date":"2024-09-28","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2410.01843v1","page_url":"https://thequant.space/flowcharts/optimizing-time-series-forecasting-a-comparative-study-of-a/","scores":{"empirical_rigor":7,"math_complexity":3.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper compares Adam and Nesterov Accelerated Gradient optimizers on LSTM and GRU networks for stock price time‑series forecasting.","quote":"This paper examines the effectiveness of Adam and Nesterov’s Accelerated Gradient (NAG) optimization techniques on LSTM and GRU neural networks for time series prediction, specifically stock market time‑series.","summary":"Several studies have discussed the impact different optimization techniques in the context of time series forecasting across different Neural network architectures. This paper examines the effectiveness of Adam and Nesterov’s Accelerated Gradient (NAG) optimization techniques on LSTM and GRU neural…","strategy":"GRU model optimized with Adam"},"assumptions":{"status":"available","items":[{"assumption":"The study is limited to stock market data due to limited computational resources.","type":"data","stated":"explicit","quote":"The experiments carried out in this study however are only limited to stock market data due to limited computational resources."},{"assumption":"The dataset is small, which may affect validation loss variability.","type":"data","stated":"explicit","quote":"Another limitation was that the data used for training, validation and testing was not very big."},{"assumption":"Only daily closing prices of Apple Inc. are used, assuming they represent the underlying price dynamics.","type":"market","stated":"explicit","quote":"We will be using a dataset from Yahoo Finance containing the daily closing prices of Apple Inc.’s stock between 2014 and the present month (August 2024)."}]},"datasets":{"status":"available","items":[{"name":"Apple Inc. daily closing prices","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"2014-2024","universe":"Apple Inc.","quote":"We will be using a dataset from Yahoo Finance containing the daily closing prices of Apple Inc.’s stock between 2014 and the present month (August 2024)","known_id":"yahoo-finance"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"3.2 Datasets for time-series forecasting 3.2.1 Overview of Selected Dataset We will be using a dataset from Yahoo Finance containing the daily closing prices of Apple Inc.’s stock between 2014 and the present month (August 2024), giving us an insight into how the stock’s value has changed over the last decade.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":"Apple Inc. closing price","asset_class":"equities","frequency":"daily"},"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":"GRU model optimized with Adam achieved the lowest RMSE (172.4037), outperforming all other model‑optimizer combinations.","kind":"predictive-accuracy","quote":"The GRU model optimized with Adam produced the lowest RMSE, outperforming the other model-optimizer combinations in both accuracy and convergence speed."},{"finding":"GRU models outperformed LSTM models for both Adam and NAG optimizers.","kind":"performance","quote":"The GRU models with both optimizers outperformed the LSTM models, whilst the Adam optimizer outperformed the NAG optimizer for both model architectures."},{"finding":"Adam optimizer consistently yielded lower RMSE and final losses than NAG across both architectures.","kind":"performance","quote":"Regarding their impact as optimizers, it has been observed that the use of Adam as an optimizer always results in decreased values of RMSE and final losses as opposed to NAG."},{"finding":"RMSE values: LSTM‑Adam 176.6259, LSTM‑NAG 187.6416, GRU‑Adam 172.4037, GRU‑NAG 182.2570.","kind":"predictive-accuracy","quote":"RMSE values for each model and optimizer are summarized in the table. Adam’s GRU has the lowest RMSE (172.4037)"}],"reported_performance":{"strategy":"GRU model optimized with Adam","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"available","supports":[],"contradicts":[{"paper":{"paper_id":"2603.02620","title":"Same Error, Different Function: The Optimizer as an Implicit Prior in Financial Time Series","paper_date":"2026-03-03","authors":["Federico Vittorio Cortesi","Giuseppe Iannone","Giulia Crippa","Tomaso Poggio","Pierfrancesco Beneventano"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/same-error-different-function-the-optimizer-as-an-implicit-prior-in-financial/"},"question":"Which optimizer yields better forecasting performance on financial time series?","this_paper_finding":"Adam optimizer consistently yielded lower RMSE and final losses than NAG across both architectures.","other_paper_finding":"Predictive accuracy (NMSE) remains unchanged across architectures and optimizers despite functional divergence.","other_paper_quote":"Across architectures, predictive accuracy remains unchanged, yet optimizer choice reshapes non‑linear response profiles and temporal dependence differently.","note":"A reports Adam gives lower RMSE and final loss than NAG; B reports NMSE unchanged across optimizers, contradicting A.","confidence":0.733}],"qualifies":[],"compared_with":24,"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":true,"code_url":"https://github.com/AhmadMak/Time-Series-Optimization-Research","note":null},"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":"2026-11-14T18:01:00Z"},"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/"}