{"paper_id":"2409.02277","title":"Attention-Based Reading, Highlighting, and Forecasting of the Limit Order Book","authors":["Jiwon Jung","Kiseop Lee"],"paper_date":"2024-09-03","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2409.02277v2","page_url":"https://thequant.space/flowcharts/attention-based-reading-highlighting-and-forecasting-of-th/","scores":{"empirical_rigor":4,"math_complexity":8,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes an attention‑based forecasting model for the full limit order book that uses a novel compound multivariate embedding to capture spatiotemporal relationships.","quote":"Our main contribution is the development of a compound multivariate embedding method designed to capture the complex relationships between spatiotemporal features.","summary":"Managing high-frequency data in a limit order book (LOB) is a complex task that often exceeds the capabilities of conventional time-series forecasting models. Accurately predicting the entire multi-level LOB, beyond just the mid-price, is essential for understanding high-frequency market dynamics.…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The number of price/volume levels is fixed at five for both bid and ask sides.","type":"data","stated":"explicit","quote":"To maintain consistency, we fix the number of levels, K, at 5 for both bid and ask orders in our experiments."},{"assumption":"Timestamps are standardized to equal 5‑second intervals.","type":"data","stated":"explicit","quote":"We standardized the timestamps to equal intervals of 5 seconds during data cleansing."},{"assumption":"Percent‑change transformation makes price series stationary for training.","type":"model","stated":"explicit","quote":"In our experiment, we employ percent-change transformation of prices to facilitate training."},{"assumption":"Min‑max scaling is applied variable‑wise to prevent large‑fluctuation variables from dominating the model.","type":"model","stated":"explicit","quote":"During training, we also apply min-max scaling to price and volume on a variable-wise basis to ensure that variables with large fluctuations do not disproportionately influence the model."},{"assumption":"Linear‑attention (Performer) approximates full attention with linear complexity.","type":"model","stated":"explicit","quote":"In our experiment, we use the Performer method (Choromanski et al. 2020) to enhance computational efficiency, which approximates attention with linear space and time complexity."},{"assumption":"The ordinal price ordering across LOB levels must be respected during training.","type":"model","stated":"explicit","quote":"For any fixed i-th LOB snapshot, the multi-level price structure is given by: pa k1i < pa k2i for all k1 < k2, ..."}]},"datasets":{"status":"available","items":[{"name":"LOBSTER","provider":"Huang & Polak 2011","kind":"order-book","access":"public","period":"June 21, 2012 (single trading day)","universe":"AAPL, GOOG, INTC, MSFT, AMZN","quote":"We specifically focus on five major technology companies: AAPL, GOOG, INTC, MSFT, and AMZN. The sample covers the trading day of June 21, 2012,","known_id":"lobster"}],"known":[{"id":"lobster","name":"LOBSTER","provider":"LOBSTER","kind":"order-book","access":"commercial","quote":"Data structure and preparation We utilize the LOBSTER dataset (Huang & Polak 2011), which offers real-world LOB data, including both message and order book information for selected stocks.","mentions":1,"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":"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":"Combining percent‑change and min‑max scaling yields the lowest forecasting error (MSE = 0.0464, MAE = 0.1260) among all tested transformations.","kind":"performance","quote":"the combined approach, using both percent-change and min-max scaling, achieves the lowest error rates with an MSE of 0.0464 and an MAE of 0.1260, outperforming each transformation used individually."},{"finding":"Overall, the method consistently outperforms existing multivariate forecasting approaches, achieving the lowest forecasting errors while preserving the LOB’s ordinal structure.","kind":"performance","quote":"empirical results demonstrate that our approach consistently outperforms existing multivariate forecasting methods, achieving the lowest forecasting errors while maintaining the ordinal structure of the LOB."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":12,"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":"2026-11-14T18:03:26Z"},"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/"}