{"paper_id":"2507.09734","title":"Boltzmann Price: Toward Understanding the Fair Price in High-Frequency Markets","authors":["Przemysław Rola"],"paper_date":"2025-07-13","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2507.09734v1","page_url":"https://thequant.space/flowcharts/boltzmann-price-toward-understanding-the-fair-price-in-high/","scores":{"empirical_rigor":6,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper introduces the Boltzmann price, a novel fair price derived from the Maximum Entropy Principle, and a price dynamics model where drift and volatility are driven by volume imbalance.","quote":"In this study, we introduce a novel price—the Boltzmann price—derived using the Maximum Entropy Principle.","summary":"In this paper, we introduce a parametrized family of prices derived from the Maximum Entropy Principle. The price is obtained from the distribution that minimizes bias, given the bid and ask volume imbalance at the top of the order book. Under specific parameter choices, it closely approximates the…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"State probabilities of bid and ask depend only on the top‑of‑book volume imbalance.","type":"model","stated":"explicit","quote":"Assumption 3.1. The state probabilities pb = P(X = sb) and pa = P(X = sa) depend only on the volume imbalance q."},{"assumption":"The bid‑ask spread is constant over time.","type":"model","stated":"explicit","quote":"For now, we assume that the spread St is constant over time, that is, St = S."},{"assumption":"The TOB volume imbalance reflects all information available in the market concerning the fundamental value of the asset.","type":"market","stated":"explicit","quote":"In other words, the TOB volume imbalance reflects all information available"}]},"datasets":{"status":"available","items":[{"name":"Refinitiv Eikon data","provider":"Refinitiv Eikon","kind":"order-book","access":"commercial","period":"May 2025","universe":"NYSE and NASDAQ stocks (GE and LCID)","quote":"... The final sample consists of approximately 8,000 observations across 21 trading days.","known_id":"refinitiv"}],"known":[{"id":"refinitiv","name":"Refinitiv / LSEG (Datastream, Eikon, Tick History)","provider":"LSEG","kind":"market-prices","access":"commercial","quote":"For historical data analysis, we used data obtained from Refinitiv Eikon.","mentions":2,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R4a","candidates":{"front_matter":"n/a","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Half the spread S/2 is treated as the transaction cost of crossing the spread; additional temporary impact h(νt) is also modeled.","card_quote":"where S is the bid‑ask spread (assumed constant), and h(νt) represents the temporary market impact.","meaning":"the paper reports no trading or execution result; the cost the extractor found is a model parameter"},"results":{"status":"available","evaluation_type":"pricing-calibration","findings":[{"finding":"The Boltzmann price dynamics generate higher kurtosis and heavier tails than standard Bachelier or GBM models.","kind":"theoretical","quote":"Our results show that this model naturally generates higher kurtosis and heavier tails compared to, for example, the Bachelier"},{"finding":"Empirical kurtosis: mid‑price 6.99, Boltzmann (β=0.5) 7.54, Boltzmann (β=1) 8.08, weighted‑mid 9.1.","kind":"statistical","quote":"We computed a kurtosis of 6.99 for the mid‑price changes, approximately 7.54 for the Boltzmann price changes with β = 0.5, 8.08 for the Boltzmann price with β = 1, and 9.1 for the weighted‑mid price changes."},{"finding":"Simulated price changes using the Boltzmann dynamics match historical distributions, with sampled kurtosis around 6.74–6.84 after rounding.","kind":"performance","quote":"The kurtosis of the sampled price changes is 6.74, compared to 6.99 in the historical data. After rounding the sampled price changes to two decimal places, the kurtosis increases marginally to 6.84."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":27,"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":"2026-11-14T17:32:53Z"},"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/"}