{"paper_id":"2405.11431","title":"Review of deep learning models for crypto price prediction: implementation and evaluation","authors":["Jingyang Wu","Xinyi Zhang","Fangyixuan Huang","Haochen Zhou","Rohtiash Chandra"],"paper_date":"2024-05-19","paper_type":"survey-review","paper_url":"https://arxiv.org/pdf/2405.11431v2","page_url":"https://thequant.space/flowcharts/review-of-deep-learning-models-for-crypto-price-prediction/","scores":{"empirical_rigor":7,"math_complexity":6.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes and evaluates novel deep learning models, finding that a convolutional LSTM with a multivariate approach yields the highest prediction accuracy for cryptocurrency prices.","quote":"Our results show that the convolutional LSTM with a multivariate approach provides the best prediction accuracy in two major experimental settings.","summary":"There has been much interest in accurate cryptocurrency price forecast models by investors and researchers. Deep Learning models are prominent machine learning techniques that have transformed various fields and have shown potential for finance and economics. Although various deep learning models…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The target variable for forecasting is the closing price of cryptocurrencies.","type":"data","stated":"implied","quote":"We use MLP and ARIMA models as baseline models for Bitcoin dataset."},{"assumption":"Volatility in the training period affects model precision.","type":"market","stated":"implied","quote":"Our experimental results show that utilising a training data set with high volatility weakens the precision of our predictions."},{"assumption":"Multivariate models can incorporate highly correlated cryptocurrency and macro variables to improve forecasts.","type":"model","stated":"implied","quote":"the multivariate strategy featuring a highly correlated cryptocurrency data enhanced prediction accuracy significantly, in comparison to the univariate strategy."}]},"datasets":{"status":"available","items":[{"name":"Cryptocurrency price dataset (Bitcoin, Ethereum, Dogecoin, Litecoin)","provider":null,"kind":"market-prices","access":"unknown","period":"29/04/2013-01/04/2024 (Bitcoin); 08/08/2","universe":"Bitcoin, Ethereum, Dogecoin, Litecoin","quote":"Table 5: Statistical description of the dataset, where the size refers to the number of data points (days)."},{"name":"Multivariate model dataset splits","provider":null,"kind":"market-prices","access":"unknown","period":"Various train/test splits from 2013 to 2","universe":"Each cryptocurrency (Bitcoin, Ethereum, Dogecoin, Litecoin)","quote":"Table 7: Time span of training and test dataset in different experiments for each cryptocurrency."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"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 convolutional LSTM with a multivariate approach achieved the highest prediction accuracy across both pre‑COVID‑19 and COVID‑19 experimental settings.","kind":"predictive-accuracy","quote":"Our results show that the convolutional LSTM with a multivariate approach provides the best prediction accuracy in two major experimental settings."},{"finding":"Multivariate deep learning models outperformed univariate models in forecasting the four cryptocurrencies.","kind":"performance","quote":"Our results also indicate that the multivariate deep learning models exhibit better performance in forecasting four different cryptocurrencies when compared to the univariate models."},{"finding":"Experiment 2 (COVID‑19 training data) yielded lower model accuracy than Experiment 1 (pre‑COVID‑19 training data).","kind":"performance","quote":"Generally, we found that Experiment 2 has lower model accuracy than Experiment 1, since the latter features data during COVID-19 which features phases of high volatility."},{"finding":"The Conv‑LSTM model provided the most accurate predictions under the Multivariate* approach, with minimal accuracy loss between 1‑day and 5‑day horizons.","kind":"predictive-accuracy","quote":"Conv‑LSTM model provides the most accurate predictions when employing this strategy for forecasting cryptocurrencies for both experiments."},{"finding":"CNN models performed worst among the deep learning architectures for the multivariate strategy.","kind":"performance","quote":"We notice that CNN provides the worst accuracy formed by the Transformer model in both strategies."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":26,"citations":{"cited_by_in_corpus":1,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":1},"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":"2026-11-14T18:09:17Z"},"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/"}