{"paper_id":"2401.00603","title":"Intraday Trading Algorithm for Predicting Cryptocurrency Price Movements Using Twitter Big Data Analysis","authors":["Vahidin Jeleskovic","Stephen Mackay"],"paper_date":"2023-12-31","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2401.00603v1","page_url":"https://thequant.space/flowcharts/intraday-trading-algorithm-for-predicting-cryptocurrency-pri/","scores":{"empirical_rigor":3,"math_complexity":2.5,"quadrant":"Philosophers"},"proposes":{"status":"available","statement":"The paper proposes a basic intraday trading algorithm that uses Twitter foundation channel messages to decide buy or sell actions within a 15‑minute window.","quote":"the algorithm collects data from Twitter, analyzes the tweet, decides whether to buy or sell a cryptocurrency and the time of execution.","summary":"Cryptocurrencies have emerged as a novel financial asset garnering significant attention in recent years. A defining characteristic of these digital currencies is their pronounced short-term market volatility, primarily influenced by widespread sentiment polarization, particularly on social media…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Twitter messages from cryptocurrency foundations affect price movements within 15 minutes.","type":"market","stated":"explicit","quote":"\"Twitter messages from cryptocurrencies foundations have an impact on price movements within 15 minutes.\""},{"assumption":"Traders react to tweet information within approximately three minutes.","type":"execution","stated":"implied","quote":"The empirical findings reveal statistically significant increases in return rates, particularly within the initial three minutes following tweet publication."},{"assumption":"The Binance API provides accurate 1‑minute candlestick data for all exchange pairs used in the analysis.","type":"data","stated":"explicit","quote":"The API of Binance provides candlestick data in 1‑minute intervals for every exchange pair."},{"assumption":"Transaction fees are as reported for each exchange and remain constant during the trading horizon.","type":"model","stated":"explicit","quote":"The trading fees on Binance are generally 0.1%, but they can be reduced by 25% if the trader holds Binance Coins (BNB) resulting in a potential fee of 0.075%."},{"assumption":"Retweets contain no new information and only affect price when the lag is short (≤3 minutes).","type":"other","stated":"explicit","quote":"When assuming a maximal retweet lag of 3 minutes, the message has a higher impact that results in a maximal cumulative return of 0.0008 at t5."}]},"datasets":{"status":"available","items":[{"name":"Binance candlestick data","provider":"Binance","kind":"market-prices","access":"public","period":null,"universe":null,"quote":"The API of Binance provides candlestick data in 1‑minute intervals for every exchange pair.","known_id":"binance"}],"known":[{"id":"twitter","name":"Twitter / X","provider":"X Corp.","kind":"text-news","access":"public","quote":"In contrast to the findings that the Twitter sentiment of tweets in the whole network6162, the sentiment of specific messages from foundations channels had","mentions":96,"used_in":20},{"id":"binance","name":"Binance","provider":"Binance","kind":"market-prices","access":"public","quote":"This function was used to obtain the latest 3,200 Tweets from the altcoins official channels that are listed on Binance.","mentions":32,"used_in":6}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"available","modeled":"partial","headline_net_of_costs":null,"detail":"Fees 0.1% (reduced to 0.075% with BNB) on Binance; 0.2% on DigiFinex, Huobi, ZB.COM; buyer fee 0.02‑0.1% and seller fee 0.05‑0.15% on OKEx.","quote":"are 0.2% per trade. OKEx offers a volume based discount model, where they differentiate between buyer and seller. The fee for buyers ranges from 0.02% to 0.1%...","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"partial","evidence_card_quoted":true},"card_detail":"Fees 0.1% (reduced to 0.075% with BNB) on Binance; 0.2% on DigiFinex, Huobi, ZB.COM; buyer fee 0.02‑0.1% and seller fee 0.05‑0.15% on OKEx.","card_quote":"are 0.2% per trade. OKEx offers a volume based discount model, where they differentiate between buyer and seller. The fee for buyers ranges from 0.02% to 0.1%...","meaning":"costs appear only as a robustness check, a flat fee without spread or impact, or outside the headline numbers"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Return rates increase significantly within the first three minutes after a foundation tweet is published.","kind":"statistical","quote":"The empirical findings reveal statistically significant increases in return rates, particularly within the initial three minutes following tweet publication."},{"finding":"Sentiment of foundation tweets has no discernible impact on cryptocurrency price movements.","kind":"negative","quote":"Surprisingly, sentiments were found to have no discerni-ble impact on cryptocurrency price movements."},{"finding":"The basic trading algorithm yields some benefits in the 15‑minute window but these benefits are not statistically significant.","kind":"performance","quote":"While the basic trading algorithm presented in this study does yield some benefits within the 15‑minute timeframe, these benefits are not statistically significant."},{"finding":"Retweets have a minimal impact, with a maximal cumulative excess return of 0.0002 at t5.","kind":"performance","quote":"Retweets seem to have only a little impact on price movements from t1 to t5, reaching a maximal cumulative excess return of 0.0002."},{"finding":"When retweet lag is ≤3 minutes, the maximal cumulative return reaches 0.0008 at t5.","kind":"performance","quote":"When assuming a maximal retweet lag of 3 minutes, the message has a higher impact that results in a maximal cumulative return of 0.0008 at t5."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[{"paper":{"paper_id":"2302.11371","title":"FTX's downfall and Binance's consolidation: The fragility of centralised digital finance","paper_date":"2023-02-22","authors":["David Vidal-Tomás","Antonio Briola","Tomaso Aste"],"empirical_rigor":7.5,"page_url":"https://thequant.space/flowcharts/ftxs-downfall-and-binances-consolidation-the-fragility-of-centralised-digital/"},"question":"Does Twitter activity influence cryptocurrency price movements?","this_paper_finding":"Sentiment of foundation tweets has no discernible impact on cryptocurrency price movements.","other_paper_finding":"Binance tweets actively accelerated the collapse, causing a systemic reaction in the cryptocurrency market.","other_paper_quote":"Results suggest that the collapse was actively accelerated by Binance tweets causing a systemic reaction in the cryptocurrency market.","note":"Finding A shows Binance tweets accelerated a market collapse, while Finding B reports a 0 discernible impact from foundation tweets.","confidence":0.598}],"qualifies":[],"compared_with":21,"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":"2026-11-14T16:28:53Z"},"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/"}