{"paper_id":"2411.13594","title":"High resolution microprice estimates from limit orderbook data using hyperdimensional vector Tsetlin Machines","authors":["Christian D. Blakely"],"paper_date":"2024-11-18","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2411.13594v1","page_url":"https://thequant.space/flowcharts/high-resolution-microprice-estimates-from-limit-orderbook-da/","scores":{"empirical_rigor":7,"math_complexity":8,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes an error‑correcting model for the microprice that uses higher‑order order‑book imbalance information and a hyperdimensional vector Tsetlin machine for fast estimation.","quote":"We propose an error-correcting model for the microprice, a high-frequency estimator of future prices given higher order information of imbalances in the orderbook.","summary":"We propose an error-correcting model for the microprice, a high-frequency estimator of future prices given higher order information of imbalances in the orderbook. The model takes into account a current microprice estimate given the spread and best bid to ask imbalance, and adjusts the microprice…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The features extracted from higher‑order depth must be computed fast enough to remain relevant for the next order‑book event.","type":"execution","stated":"implied","quote":"these features need to be extracted and evaluated in a fast enough manner to be still relevant during the next event of the orderbook."},{"assumption":"A fully trained Tsetlin machine is available at prediction time to adjust the microprice.","type":"model","stated":"explicit","quote":"we assume a fully trained TM in order make the predictions in how to adjust the microprice."},{"assumption":"Level‑3 order‑book data from Databento accurately represents the market microstructure for the equities studied.","type":"data","stated":"implied","quote":"using orderbook data from level 3 orderbook data provided by Databento"}]},"datasets":{"status":"available","items":[{"name":"Level‑3 order‑book data","provider":"Databento","kind":"order-book","access":"commercial","period":null,"universe":"TEM (small‑cap) and TSLA (blue‑chip) equities","quote":"Data is provided by Databento."}],"known":[],"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":"unclear","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"The error‑correcting estimator provides a more robust forecast of future prices compared with the baseline microprice.","kind":"predictive-accuracy","quote":"demonstrate empirically that this estimator can provide a robust estimate of future prices in the orderbook."},{"finding":"Adjusted microprice shows slightly better accuracy when spreads are tighter and imbalance is near zero, especially for blue‑chip equities like TSLA.","kind":"performance","quote":"The empirical results so far have demonstrated slightly better accuracy at measuring a microprice adjustment when the spreads are tighter and there the imbalance is centered around zero which is the case often with blue chip equities such as TSLA."},{"finding":"When spreads are tight, the adjusted microprice performs similarly to the original microprice during later trading sessions.","kind":"performance","quote":"We also see that the adjusted microprice tends to perform the same as the microprice when spreads are more tight as trading continues during the afternoon trading session as volatility dies down."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":14,"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":"2026-11-14T17:53:26Z"},"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/"}