{"paper_id":"2409.14157","title":"Price predictability in limit order book with deep learning model","authors":["Kyungsub Lee"],"paper_date":"2024-09-21","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2409.14157v1","page_url":"https://thequant.space/flowcharts/price-predictability-in-limit-order-book-with-deep-learning/","scores":{"empirical_rigor":7,"math_complexity":4.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a deep learning model that predicts high‑frequency price changes using only Level 1 order‑book data, achieving comparable performance to models using the full LOB.","quote":"Using only Level 1 data produced results comparable to those of the entire LOB dataset.","summary":"This study explores the prediction of high-frequency price changes using deep learning models. Although state-of-the-art methods perform well, their complexity impedes the understanding of successful predictions. We found that an inadequately defined target price process may render predictions…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Analysis is restricted to standard trading hours (09:30‑16:00).","type":"data","stated":"explicit","quote":"We use the data only from standard trading hours, 09:30 to 16:00, which contain approximately…"},{"assumption":"The target variable is the modified return r_{k,k'}(t) defined without future information for r_{1,k}(t).","type":"model","stated":"explicit","quote":"The target variable is r1,k(t) = fk(t) −p1(t) / p1(t) which calculates the modiﬁed return based on a current price p1(t) as in Ntakaris et al. (2018)."},{"assumption":"Classes are balanced by choosing a constant α for the three‑class problem.","type":"model","stated":"explicit","quote":"Instances are classiﬁed as UP : y > α, DOWN : y < −α, STABLE : |y| ≤α for some constant α chosen to balance the class distribution."},{"assumption":"Model training uses the preceding 20 days of data for each daily evaluation.","type":"execution","stated":"explicit","quote":"Model evaluation occurs on a daily basis throughout 2022. For each evaluation, the model is trained using data from the preceding 20 days."},{"assumption":"Volatility and directional predictability are evaluated separately using the STABLE/DIVERGE split.","type":"statistical","stated":"explicit","quote":"Volatility accuracy is the correct STABLE/DIVERGE prediction rate, while directional accuracy is the UP/DOWN hit ratio within correctly identified DIVERGE cases."}]},"datasets":{"status":"available","items":[{"name":"AAPL 2022 LOB data","provider":"Nasdaq TotalView ITCH","kind":"order-book","access":"commercial","period":"2022","universe":"Apple Inc. (AAPL) stock","quote":"Our analysis uses highly active trading data for AAPL (Apple Inc.) stocks in 2022 from Nasdaq TotalView ITCH. These data provide detailed order book information, displaying the top 10 bid and ask price levels, share volume at each level, and timestamps for transactions.","known_id":"itch"}],"known":[{"id":"itch","name":"Nasdaq TotalView-ITCH","provider":"Nasdaq","kind":"order-book","access":"commercial","quote":"Our analysis uses highly active trading data for AAPL (Apple Inc.) stocks in 2022 from Nasdaq TotalView ITCH.","mentions":2,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"l2-book"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"n/a","evidence_card":"no","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"Overall classification accuracy using Level 1 data is 53.6%, matching the full‑LOB model.","kind":"predictive-accuracy","quote":"When combined, the overall accuracy is 53.6%."},{"finding":"Volatility prediction accuracy reaches 69.4% on Level 1 data.","kind":"predictive-accuracy","quote":"DIVERGE ... The average accuracy of the volatility prediction is 69.4% as in the ﬁrst column in Table 7."},{"finding":"Directional prediction accuracy for DIVERGE cases is 71.1% using Level 1 data.","kind":"predictive-accuracy","quote":"For DIVERGE, the procedure subsequently classiﬁes UP or DOWN, achieving an average directional prediction accuracy of 71.1%."},{"finding":"Using only price information yields a directional accuracy of about 50%, supporting the efficient market hypothesis.","kind":"predictive-accuracy","quote":"An interesting observation is that predictions based solely on price processes result in a consistent 50% directional accuracy, see Figure 3. Relying on price processes alone cannot forecast future price directions underscoring the eﬃcient market hypothesis (Fama, 1970)."},{"finding":"Incorporating volume imbalance markedly improves directional prediction performance.","kind":"performance","quote":"The same analysis on AMZN, NVDA, and MSFT in 2022 yields similar results."}],"reported_performance":null,"out_of_sample":{"method":"walk-forward","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[{"paper":{"paper_id":"2507.16701","title":"Binary Tree Option Pricing Under Market Microstructure Effects: A Random Forest Approach","paper_date":"2025-07-22","authors":["Akash Deep","Chris Monico","W. Brent Lindquist","Svetlozar T. Rachev","Frank J. Fabozzi"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/binary-tree-option-pricing-under-market-microstructure-effec/"},"question":"Does order flow (volume) imbalance improve directional price prediction?","this_paper_finding":"Incorporating volume imbalance markedly improves directional prediction performance.","other_paper_finding":"Order flow imbalance is the most important predictor, contributing 43.2% to feature importance.","other_paper_quote":"Order flow imbalance is identified as the most influential predictor, contributing 43.2% to feature importance.","note":"Both find imbalance boosts prediction; A shows marked improvement, B assigns 43.2% feature importance.","confidence":0.675}],"contradicts":[],"qualifies":[],"compared_with":47,"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":"2026-11-14T18:01:35Z"},"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/"}