Paper: arXiv 2511.04469

Authors: Dennis Thumm, Luis Ontaneda Mijares

Abstract

Market generators using deep generative models have shown promise for synthetic financial data generation, but existing approaches lack causal reasoning capabilities essential for counterfactual analysis and risk assessment. We propose a Time-series Neural Causal Model VAE (TNCM-VAE) that combines variational autoencoders with structural causal models to generate counterfactual financial time series while preserving both temporal dependencies and causal relationships. Our approach enforces causal constraints through directed acyclic graphs in the decoder architecture and employs the causal Wasserstein distance for training. We validate our method on synthetic autoregressive models inspired by the Ornstein-Uhlenbeck process, demonstrating superior performance in counterfactual probability estimation with L1 distances as low as 0.03-0.10 compared to ground truth. The model enables financial stress testing, scenario analysis, and enhanced backtesting by generating plausible counterfactual market trajectories that respect underlying causal mechanisms.

Complexity vs Empirical Score

  • Math Complexity: 7.5/10
  • Empirical Rigor: 6.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper presents advanced mathematical concepts including variational autoencoders, structural causal models, DAGs, and the causal Wasserstein distance, indicating high mathematical complexity. However, while it includes concrete experiments on synthetic data with reported metrics (L1 distances) and mentions practical applications like stress testing and backtesting, the empirical validation is limited to controlled synthetic environments rather than live market data, placing it in the high-rigor but not fully backtest-ready category.

Research Flowchart

  flowchart TD
  A["Research Goal: Causal Market Simulator for Counterfactual Analysis"] --> B["Methodology: TNCM-VAE Architecture"]
  B --> C["Input: Synthetic Data "Ornstein-Uhlenbeck""]
  B --> D["Process: Structural Causal Model + VAE Decoder"]
  D --> E["Process: Causal Wasserstein Distance Training"]
  E --> F["Computational: Enforcing DAG Constraints"]
  F --> G["Outcome: Low L1 Distance 0.03-0.10"]
  G --> H["Outcome: Financial Stress Testing & Scenario Analysis"]

Cited References (225)

  1. The patent holder’s dilemma: Buy, sell, or troll? (2007) — link
  2. Deciding equivalances among conjunctive aggregate queries (2007) — link
  3. Special issue: Digital Libraries (1996)
  4. Understanding Policy-Based Networking (2001)
  5. First-Order Dynamic Logic (1979) — link
  6. The title of book one (2007) — link
  7. The title of book two (2008) — link
  8. Achieving application requirements (1990) — link
and 217 more
  1. Statecarts in use: structured analysis and object-orientation (1998) — link
  2. The Art of Computer Programming, Vol. 1: Fundamental Algorithms (3rd. ed.) (1997)
  3. The Art of Computer Programming (1998)
  4. An experiment in bibliographic mark-up: Parsing metadata for XML export (2010) — link
  5. Catch me, if you can: Evading network signatures with web-based polymorphic worms (2007)
  6. Catch me, if you can: Evading network signatures with web-based polymorphic worms (2008)
  7. Catch me, if you can: Evading network signatures with web-based polymorphic worms (2009)
  8. Predicate Path expressions (1979) — link
  9. LOGICS of Programs: AXIOMATICS and DESCRIPTIVE POWER (1978)
  10. Optimal Motion Control of a Ground Vehicle (2003)
  11. Algorithms for Closest-Point Problems (Computational Geometry) (1985)
  12. Introduction to Bayesian Statistics (2001) — link
  13. CLIFFORD: a Maple 11 Package for Clifford Algebra Computations, version 11 (2007) — link
  14. Stats and Analysis (2006) — link
  15. A more perfect union (2008) — link
  16. The fountain of youth (2009)
  17. Solder man (2003) — link
  18. Interview with Bill Kinder: January 13, 2005 (2005) — link
  19. The Enabling of Digital Libraries (2008)
  20. (old) Finding minimum congestion spanning trees (2000) — link
  21. (new) Finding minimum congestion spanning trees (2000) — link
  22. (old) Distributed data source verification in wireless sensor networks (2009) — link
  23. (new) Distributed data source verification in wireless sensor networks (2009) — link
  24. Portalis: using competitive online interactions to support aid initiatives for the homeless (2008) — link
  25. Visual Basic 6: Design, Specification, and Objects with Other (1999)
  26. The Latex Web Companion: Integrating TEX, HTML, and XML (1999)
  27. Vertex Types in Book-Embeddings (1987)
  28. Vertex Types in Book-Embeddings (1987)
  29. CHI ‘08: CHI ‘08 extended abstracts on Human factors in computing systems (2008)
  30. Algorithms for Closest-Point Problems (Computational Geometry) (1985)
  31. IEEE TCSC Executive Committee (2004) — link
  32. Distributed systems (2nd Ed.) (1993)
  33. New Algorithms for Dependency-Directed Backtracking (Master’s thesis) (1986)
  34. New Algorithms for Dependency-Directed Backtracking (Master’s thesis) (1986)
  35. Seminumerical Algorithms (1981)
  36. E-commerce and cultural values (2001) — link
  37. Chapter 9 (2002) — link
  38. The implementation of electronic commerce in SMEs in Singapore (Incoll) (2003) — link
  39. E-commerce and cultural values - (InBook-num-in-chap) (2004) — link
  40. E-commerce and cultural values (Inbook-text-in-chap) (2005) — link
  41. E-commerce and cultural values (Inbook-num chap) (2006) — link
  42. A library-based synthesis methodology for reversible logic (2010)
  43. Synthesis of Reversible Circuit Using Cycle-Based Approach (2010)
  44. Algorithmic Enumeration of Ideal Classes for Quaternion Orders (2010) — link
  45. Chapter II: Notes on data structuring (1972) — link
  46. Transcript of question and answer session (1981) — link
  47. Go to statement considered harmful (1979) — link
  48. Three-dimensional virtual acoustic displays (1992) — link
  49. Managerial expert systems and organizational change: some critical research issues (1987) — link
  50. Simplified Structured COBOL with Microsoft/MicroFocus COBOL (1990)
  51. A multi-radio unification protocol for IEEE 802.11 wireless networks (2004)
  52. Wireless Sensor Networks: A Survey (2002)
  53. A Survey on Wireless Multimedia Sensor Networks (2007)
  54. SSCH : Slotted Seeded Channel Hopping for Capacity Improvement in IEEE 802.11 Ad-Hoc Wireless Networks (2004)
  55. XBOW Sensor Motes Specifications (2008)
  56. Overview of Sensor Networks (2004)
  57. CodeBlue : Sensor Networks for Medical Care (2008)
  58. Investigating Network Architectures for Body Sensor Networks (2007) — link
  59. Channel-Hopping Multiple Access (2000)
  60. Body Sensor Networks (2008)
  61. Mapping Powerlists onto Hypercubes (1994)
  62. Automatic Parallelization for Distributed-Memory Multiprocessing Systems (1989)
  63. User recovery and reversal in interactive systems (1984)
  64. Generalizing specifications for uniformly implemented loops (1985)
  65. Towards monolingual programming environments (1985)
  66. The \TeX book (1984)
  67. Distributed algorithms for finding centers and medians in networks (1984)
  68. \it \LaTeX : A Document Preparation System (1986)
  69. Program transformations in a denotational setting (1985)
  70. Seminumerical Algorithms (1981)
  71. A high-level approach to computer document formatting (1980)
  72. A multifrequency MAC specially designed for wireless sensor network applications (2010) — link
  73. Institutional members of the \TeX Users Group (2017) — link
  74. acmart— Class for typesetting publications of ACM (2017) — link
  75. The \textsl doclicense package (2022) — link
  76. Reasoning About Naming Systems (1993) — link
  77. Babel, a Multilingual Style-Option System for Use with LaTeX’s Standard Document Styles (1991)
  78. A Methodology for Implementing Highly Concurrent Data Objects (1993) — link
  79. Publication quality tables in \LaTeX (2005)
  80. Using the amsthm Package (2015)
  81. R: A Language and Environment for Statistical Computing (2019) — link
  82. UMass Citation Field Extraction Dataset (2013) — link
  83. Citation concept analysis (CCA) —A new form of citation analysis revealing the usefulness of concepts for other researchers illustrated by two exemplary case studies including classic books by Thomas S.~Kuhn and Karl R.~Popper (2019) — link
  84. Learning Soft Linear Constraints with Application to Citation Field Extraction (2014) — link
  85. Maintaining Discrete Probability Distributions Optimally (1993)
  86. Causal data science for financial stress testing (2018)
  87. Navigating Market Turbulence: Insights from Causal Network Contagion Value at Risk (2024) — link
  88. Causal Change Point Detection and Localization (2024) — link
  89. Counterfactual Image Editing (2024) — link
  90. Counterfactual Image Editing with Disentangled Causal Latent Space (2025) — link
  91. Neural Causal Models for Counterfactual Identification and Estimation (2023) — link
  92. CausalFormer: An Interpretable Transformer for Temporal Causal Discovery (2024)
  93. Towards Dynamic Structure Changes Detection in Financial Series via Causal Analysis (2021)
  94. From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modeling (2024) — link
  95. Continuous inspection schemes (1954)
  96. Point estimation of the parameters of piecewise regression models (1976)
  97. Detecting “disorder” in multidimensional random processes (1981)
  98. A new approach to the economic analysis of nonstationary time series and the business cycle (1989)
  99. On likelihood ratio tests for threshold autoregression (1990)
  100. Bayesian online changepoint detection (2007) — link
  101. Optimal detection of changepoints with a linear computational cost (2012)
  102. Wild binary segmentation for multiple change-point detection (2014)
  103. Selective review of offline change point detection methods (2020)
  104. A survey of methods for time series change point detection (2017)
  105. Automatic change-point detection in time series via deep learning (2024)
  106. Change-point detection with deep learning: A review (2025)
  107. Anomaly Detection for Time Series Using VAE-LSTM Hybrid Model (2020)
  108. STL: A seasonal-trend decomposition (1990)
  109. Forecasting, structural time series models and the Kalman filter (1990)
  110. Going Beyond Static: Understanding Shifts with Time-Series Attribution (2025)
  111. Causal inference on time series using restricted structural equation models (2013)
  112. Toward causal representation learning (2021)
  113. Invariant causal prediction for sequential data (2019)
  114. Partial Disentanglement via Mechanism Sparsity (2022)
  115. Marrying causal representation learning with dynamical systems for science (2024)
  116. Instance-based counterfactual explanations for time series classification (2021)
  117. CoMTE: Counterfactual explanations for multivariate time series (2021)
  118. A kernel two-sample test (2012)
  119. D’ya like DAGs? A survey on structure learning and causal discovery (2022)
  120. Causal-oriented representation learning for time-series forecasting based on the spatiotemporal information transformation (2025)
  121. Amortized causal discovery: Learning to infer causal graphs from time-series data (2022)
  122. Causality (2009)
  123. The Book of Why: The New Science of Cause and Effect (2018)
  124. Elements of causal inference: foundations and learning algorithms (2017)
  125. Time Series Domain Adaptation via Latent Invariant Causal Mechanism (2025) — link
  126. Change-point detection with deep learning: A review (2025)
  127. Improvement and application of back random response detection: Based on cumulative sum and change point analysis (2024)
  128. Causal-oriented representation learning for time-series forecasting based on the spatiotemporal information transformation (2025)
  129. ADIA Lab Structural Break Challenge (2025)
  130. Time- Causal VAE : Robust Financial Time Series Generator (2024) — link
  131. Causal-oriented representation learning for time-series forecasting based on the spatiotemporal information transformation (2025) — link
  132. Bayesian Online Changepoint Detection
  133. Towards Dynamic Structure Changes Detection in Financial Series via Causal Analysis (2021) — link
  134. Learning Structural Causal Models through Deep Generative Models : Methods , Guarantees , and Challenges (2024) — link
  135. Causal Inference and Data Fusion in Econometrics (2023) — link
  136. Day-ahead electricity price forecasting with high-dimensional structures: Univariate vs. multivariate modeling frameworks (2018) — link
  137. Forecasting day-ahead electricity prices: A review of state-of-the-art algorithms, best practices and an open-access benchmark (2021) — link
  138. Crafting Papers on Machine Learning (2000)
  139. The Need for Biases in Learning Generalizations (1980)
  140. Computational Complexity of Machine Learning (1989)
  141. Machine Learning: An Artificial Intelligence Approach, Vol. I (1983)
  142. Pattern Classification (2000)
  143. Suppressed for Anonymity (2021)
  144. Mechanisms of Skill Acquisition and the Law of Practice (1981)
  145. Some Studies in Machine Learning Using the Game of Checkers (1959)
  146. Vector autoregressions (2001)
  147. Time series analysis by state space methods (2012)
  148. Time series deconfounder: Estimating treatment effects over time in the presence of hidden confounders (2020)
  149. Causal discovery with attention-based convolutional neural networks (2019)
  150. Time-series generative adversarial networks (2019)
  151. Time-series generation by contrastive imitation (2021)
  152. The sensitivity of counterfactual fairness to unmeasured confounding (2020)
  153. Reintroducing Dynamics into Static Causal Models (2019)
  154. Causal Models for Dynamical Systems (2022) — link
  155. Dynamic Structural Causal Models (2024)
  156. A Dynamical View of the Question of Why (2024) — link
  157. Algorithmic Recourse: from Counterfactual Explanations to Interventions (2021) — link
  158. Optimal transport and Wasserstein distances for causal models (2024) — link
  159. On Pearl’s Hierarchy and the Foundations of Causal Inference (2022) — link
  160. Learning Structural Causal Models through Deep Generative Models: Methods, Guarantees, and Challenges (2024) — link
  161. A Survey on Causal Discovery Methods for I.I.D. and Time Series Data (2023) — link
  162. A logic for causal inference in time series with discrete and continuous variables (2011)
  163. Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations (2022)
  164. Partial counterfactual identification of continuous outcomes with a curvature sensitivity model (2023)
  165. On Pearl’s Hierarchy and the Foundations of Causal Inference (2022) — link
  166. Auto-encoding variational bayes (2013) — link
  167. Intervening and letting go: On the adequacy of equilibrium causal models (2021)
  168. Causal inference for time series (2023)
  169. Causal discovery in a complex industrial system: A time series benchmark (2024)
  170. Density estimation using Real NVP (2017) — link
  171. Causal machine learning for predicting treatment outcomes (2024)
  172. Data Generating Process to Evaluate Causal Discovery Techniques for Time Series Data (2020)
  173. The causal-neural connection: Expressiveness, learnability, and inference (2021)
  174. Temporally Disentangled Representation Learning (2022)
  175. Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems (2023)
  176. On the Identifiability of Switching Dynamical Systems (2024) — link
  177. CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discovery (2024) — link
  178. Dy CAST : Learning Dynamic Causal Structure from Time Series (2025) — link
  179. Cot-gan: Generating sequential data via causal optimal transport (2020)
  180. From optimal transport to generative modeling: the VEGAN cookbook (2017) — link
  181. Forecasting treatment responses over time using recurrent marginal structural networks (2018)
  182. Estimating counterfactual treatment outcomes over time through adversarially balanced representations (2020) — link
  183. Tts-gan: A transformer-based time-series generative adversarial network (2022)
  184. CausalVAE: Disentangled Representation Learning via Neural Structural Causal Models (2021)
  185. Weakly supervised disentangled generative causal representation learning (2022)
  186. Causal inference meets deep learning: A comprehensive survey (2024)
  187. Deep Structural Causal Models for Tractable Counterfactual Inference (2020)
  188. Partial counterfactual identification from observational and experimental data (2022)
  189. Causal machine learning for cost-effective allocation of development aid (2024)
  190. Estimating the effects of continuous-valued interventions using generative adversarial networks (2020)
  191. Causal transformer for estimating counterfactual outcomes (2022)
  192. Time Series Foundation Models for Multivariate Financial Time Series Forecasting (2025) — link
  193. AI Challenges in Mathematical Investing (2025) — link
  194. Causal discovery from temporally aggregated time series (2017)
  195. Quantitative Financial Models with Scenarios from LLM : Temporal Fusion Transformers as Alternative Monte - Carlo (2024) — link
  196. Quantitative Models with Qualitative Scenarios: Simulation with Transformer and Large Language Model (2025)
  197. Generative Models in Finance: Market Generators, a Paradigm Shift in Financial Modeling (2025)
  198. Generative Models in Finance : Market Generators , a Paradigm Shift in Financial Modeling (2025) — link
  199. Toward Automating Causal Discovery in Financial Markets and Beyond (2025)
  200. Causality-Inspired Models for Financial Time Series Forecasting (2024) — link
  201. Temporally Disentangled Representation Learning under Unknown Nonstationarity (2024) — link
  202. The market generator (2019)
  203. Empirical properties of asset returns: stylized facts and statistical issues (2001)
  204. Theoretical foundations of deep selective state-space models (2024)
  205. Quant GANs: deep generation of financial time series (2020)
  206. Generating realistic stock market order streams (2020)
  207. Backtesting (2015)
  208. Time-Causal VAE: Robust Financial Time Series Generator (2024) — link
  209. Long short-term memory (1997)
  210. On the Properties of Neural Machine Translation: Encoder–Decoder Approaches (2014)
  211. Optimal transport and Wasserstein distances for causal models (2025)
  212. The Brownian movement and stochastic equations (1942)
  213. Arbitrage theory in continuous time (2009)
  214. Diffusion Factor Models: Generating High-Dimensional Returns with Factor Structure — → 2504.06566
  215. Event-Based Limit Order Book Simulation under a Neural Hawkes Process: Application in Market-Making (2025) — link
  216. Predicting Liquidity-Aware Bond Yields using Causal GANs and Deep Reinforcement Learning with LLM Evaluation (2025) — link
  217. Do- PFN : In-Context Learning for Causal Effect Estimation (2025) — link

1 of 225 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.