{"paper_id":"2501.12676","title":"Marketron games: Self-propelling stocks vs dumb money and metastable dynamics of the Good, Bad and Ugly markets","authors":["I. Halperin","A. Itkin"],"paper_date":"2025-01-22","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2501.12676v2","page_url":"https://thequant.space/flowcharts/marketron-games-self-propelling-stocks-vs-dumb-money-and-me/","scores":{"empirical_rigor":2,"math_complexity":9,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes a nonlinear stochastic model of price formation in an inelastic market, called the marketron, incorporating money flows, impact, and self‑propulsion.","quote":"We present a model of price formation in an inelastic market whose dynamics are partially driven by both money flows and their impact on asset prices.","summary":"We present a model of price formation in an inelastic market whose dynamics are partially driven by both money flows and their impact on asset prices. The money flow to the market is viewed as an investment policy of outside investors. For the price impact effect, we use an impact function that…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Signal and market impact linearly contribute to the return.","type":"model","stated":"explicit","quote":"When writing the second line of Eq. (1), for simplicity, we assume that the signal and the market impact linearly contribute to the return rt."},{"assumption":"The random part of the return is white noise.","type":"statistical","stated":"explicit","quote":"The second assumption made is about the random part ϵt of rt, which we represent by a white noise."},{"assumption":"The market consists of a single stock (or index) offered to outside investors.","type":"market","stated":"explicit","quote":"For simplicity, in this paper we explore a stylized market that has a single stock to offer to outside investors."},{"assumption":"Impact function proportional to flow‑to‑price ratio and includes a memory variable.","type":"model","stated":"explicit","quote":"where yt is a new state variable that tracks the memory of past money flows into the stock."},{"assumption":"Memory variable yt follows an exponential moving average of the flow‑to‑price ratio.","type":"model","stated":"explicit","quote":"one intuitive way is to define it via an exponential moving average (EMA) of some function F = F(ut/St) yt = ¯y −[¯y −y(0)]e−µt − Z t 0…"},{"assumption":"Calibration uses only observable log‑price xt (e.g., S&P500) and filters unobservable yt and θt.","type":"data","stated":"explicit","quote":"Since the only observable variable in Eq. (29) is xt, one approach to calibrate the model is to fit it to the time series of the S&P500 index and use nonlinear filtering to capture the dynamics of unobservable variables yt and θt."}]},"datasets":{"status":"available","items":[{"name":"S&P500 index","provider":null,"kind":"market-prices","access":"public","period":null,"universe":null,"quote":"fit it to the time series of the S&P500 index and use nonlinear filtering to capture the dynamics of unobservable variables yt and θt."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"weekly-monthly"},"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":"pricing-calibration","findings":[{"finding":"The model predicts three distinct market regimes called Good, Bad, and Ugly.","kind":"theoretical","quote":"it predicts three distinct regimes of the market, which we call the Good, the Bad, and the Ugly markets."},{"finding":"Calibrated default intensity is about 18 basis points, aligning with market‑implied intensities of 10–50 bps.","kind":"pricing-calibration","quote":"The calibrated marketron model generates an annualized default intensity of about 18 bps, which reasonably aligns with market‑implied default intensities typically ranging from 10 to 50 bps."},{"finding":"The model reproduces volatility clustering and realistic skewness/kurtosis in log‑returns and memory variable.","kind":"statistical","quote":"Skewness and kurtosis as functions of time with the calibrated marketron model for a) log‑returns xt, and b) the memory variable yt."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":39,"citations":{"cited_by_in_corpus":6,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":5},"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":"2026-11-14T17:47:07Z"},"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/"}