{"paper_id":"2411.12748","title":"FinBERT-BiLSTM: A Deep Learning Model for Predicting Volatile Cryptocurrency Market Prices Using Market Sentiment Dynamics","authors":["Mabsur Fatin Bin Hossain","Lubna Zahan Lamia","Md Mahmudur Rahman","Md Mosaddek Khan"],"paper_date":"2024-11-02","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2411.12748v1","page_url":"https://thequant.space/flowcharts/finbert-bilstm-a-deep-learning-model-for-predicting-volatil/","scores":{"empirical_rigor":8,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a hybrid model that combines FinBERT with a Bidirectional LSTM to forecast cryptocurrency prices.","quote":"i. Tailored for the volatile cryptocurrency market, we present a combined model of FinBERT and Bi-LSTM.","summary":"Time series forecasting is a key tool in financial markets, helping to predict asset prices and guide investment decisions. In highly volatile markets, such as cryptocurrencies like Bitcoin (BTC) and Ethereum (ETH), forecasting becomes more difficult due to extreme price fluctuations driven by…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"If a decision is made to buy or sell, the transaction is assumed to occur at the same price as the closing price of the day d‑1.","type":"execution","stated":"explicit","quote":"If a decision is made to buy or sell, the transaction is assumed to occur at the same price as the closing price of the day d −1."},{"assumption":"The required amount of Bitcoin or Ethereum for purchase will always be available on the market, with no liquidity constraints.","type":"market","stated":"explicit","quote":"It is assumed that the required amount of Bitcoin or Ethereum for purchase will always be available on the market, and transactions will not fail due to liquidity constraints or other technical issues."},{"assumption":"FinBERT‑integrated models use the sentiment score from day d‑1 because the decision must be made one day in advance.","type":"model","stated":"explicit","quote":"The FinBERT‑integrated models use the sentiment score from day d −1, as the decision must be made one day in advance."}]},"datasets":{"status":"available","items":[{"name":"Historical price data","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"2023-01-01 to 2024-? (585 days)","universe":"Bitcoin (BTC) and Ethereum (ETH)","quote":"The historical price data for Bitcoin (BTC) and Ethereum (ETH) was obtained from Yahoo Finance6,","known_id":"yahoo-finance"},{"name":"Transaction rate","provider":"Coin‑Remitter","kind":"other","access":"public","period":null,"universe":"Bitcoin (BTC) and Ethereum (ETH)","quote":"we utilized a transaction rate of 0.0001 BTC for Bitcoin and 0.003 ETH for Ethereum, which includes the gas station optimization feature for Ethereum."},{"name":"News and financial text collection","provider":"Coindesk, Binance and other crypto news platforms","kind":"text-news","access":"public","period":"2023-01-01 to 2024-? (585 days)","universe":"Bitcoin (BTC) and Ethereum (ETH)","quote":"we collected news articles and financial texts from reputable cryptocurrency news platforms, including Coindesk8, Binance9 and other specialized websites","known_id":"binance"}],"known":[{"id":"twitter","name":"Twitter / X","provider":"X Corp.","kind":"text-news","access":"public","quote":"The data, sourced from Binance5, was complemented with Twitter sentiment data.","mentions":3,"used_in":1},{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"5.1.1 Historical Price Data Collection The historical price data for Bitcoin (BTC) and Ethereum (ETH) was obtained from Yahoo Finance6, a highly reputable source for reliable ﬁnancial information.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"Transaction rates of 0.0001 BTC per trade for Bitcoin and 0.003 ETH per trade for Ethereum are applied.","quote":"we utilized a transaction rate of 0.0001 BTC for Bitcoin and 0.003 ETH for Ethereum, which includes the gas station optimization feature for Ethereum.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Transaction rates of 0.0001 BTC per trade for Bitcoin and 0.003 ETH per trade for Ethereum are applied.","card_quote":"we utilized a transaction rate of 0.0001 BTC for Bitcoin and 0.003 ETH for Ethereum, which includes the gas station optimization feature for Ethereum.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"FinBERT‑Bi‑LSTM achieves the highest 30‑day future prediction accuracy of 98.25% for Bitcoin, slightly surpassing FinBERT‑LSTM (98.14%).","kind":"performance","quote":"FinBERT‑Bi‑LSTM model achieves the highest accuracy of 98.25%, slightly surpass‑ing the FinBERT‑LSTM’s 98.14% showing that our hypothesis mentioned in Section 4 works for future multi‑day forecasting."},{"finding":"FinBERT‑Bi‑LSTM reaches 98.21% intra‑day and 98.07% one‑day‑ahead prediction accuracy on Bitcoin, delivering a remarkable profit from the one‑day‑ahead strategy.","kind":"predictive-accuracy","quote":"FinBERT‑Bi‑LSTM model achieves an accuracy of 98.21% for intra‑day predictions and 98.07% for one‑day‑ahead predictions on Bitcoin (BTC), resulting in a remarkable profit from the one‑day‑ahead strategy."},{"finding":"On Ethereum, the model attains 97.5% intra‑day and 97.36% one‑day‑ahead prediction accuracy, generating a significant profit.","kind":"predictive-accuracy","quote":"On Ethereum (ETH), it achieves an accuracy of 97.5% for intra‑day predictions and 97.36% for one‑day‑ahead predictions, generating a signiﬁcant profit."},{"finding":"Maximum Data Training yields 98.3% long‑term accuracy for Bitcoin, while Validation‑Enhanced Training gives 95.25% for Ethereum.","kind":"performance","quote":"Maximum Data Training approach yields an impressive accuracy of 98.3% for BTC, while the Validation‑Enhanced Training approach performs better for ETH with an accuracy of 95.25%."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":25,"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":"2026-11-14T17:56:38Z"},"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/"}