Newest papers

Market Impact Estimation via Causal Foundation Models

Dennis Thumm, Ying Chen · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.12537 · cited by 0 works (OpenAlex) · open-access PDF

Vietnamese

Khi một nhà giao dịch chuyển đổi khoảng trống từ phương thức chuyển đổi trung bình cho một lệnh lớn, câu hỏi có liên quan không phải là "gravh{what will the price be?}", nhưng "nghĩa{what would the price have been if I didn't traded?} tác động thị trường là do đó là một số lượng nhân quả, nhưng các mô hình cổ điển (Almgren--Chriss, propagators) rút lại giá trên dòng chảy, mà là thiên vị bất cứ khi nào dòng chảy được thông báo trên tỷ giá di chuyển giá thông qua thông tin cũng như giao dịch. Chúng tôi trình bày một proof-of-concept proof-of-concept \emph{Causal Market Simulator}: một liên tục-thời gian nhân quả trước khi kết hợp dữ liệu dòng chảy (PFN) được đào tạo trên một thị trường tổng hợp trước đó trong

Machine translation (Meta M2M100); the English original follows.

Abstract

When a trader executes a large order, the relevant question is not \emph{what will the price be?} but \emph{what would the price have been had I not traded?} Market impact is thus a causal quantity, yet classical models (Almgren--Chriss, propagators) regress price on flow, which is biased whenever informed flow moves prices through information as well as trading. We present a proof-of-concept \emph{Causal Market Simulator}: a continuous-time causal prior-data fitted network (PFN) trained on a synthetic market prior in which a hidden informational flow confounds the flow--price relation by construction, with confounding strength an exact per-episode knob. On this prior, the naive estimator's bias follows a closed form we confirm empirically (up to 68\% overestimation), while the PFN tracks the unbiased true-parameter oracle at high confounding. Its \emph{do-ablated twin}, the same model with the intervention inputs removed, collapses onto the pre-window mean. Zero-shot, the model responds at the ground-truth scale to metaorders in an ABIDES limit-order book ($+0.38$ pre-onset standard deviations against seed-replay counterfactuals), and its intervention response replicates on about 2,300 detected flow bursts in BTC/ETH/SOL perpetuals and 3,800 on Nasdaq equities, evidence consistent with, though not proof of, causal transfer. Off-prior the response degrades gracefully, and split-conformal recalibration repairs interval calibration. Transfer hinges on encoding the metaorder as added flow rather than a clamped price level, not on more training. A recurrent state-space variant closes the remaining shape gap: its impact accrues over execution duration where the transformer's stays flat, raising the correlation with measured metaorder impact from $+0.68$ to between $+0.92$ and $+0.96$, at the cost of weaker on-prior deconfounding that traces to the training recipe rather than to recurrence.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Econometrics, Economics, Oracle, Flow (mathematics), Scale (ratio), Outcome (game theory)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange