TY - GEN
T1 - Modeling Inverse Demand Function with Explainable Dual Neural Networks
AU - Cao, Zhiyu
AU - Chen, Zihan
AU - Mishra, Prerna
AU - Amini, Hamed
AU - Feinstein, Zachary
N1 - Publisher Copyright:
© 2023 ACM.
PY - 2023/11/27
Y1 - 2023/11/27
N2 - Financial contagion has been widely recognized as a fundamental risk to the financial system. Particularly potent is price-mediated contagion, wherein forced liquidations by firms depress asset prices and propagate financial stress, enabling crises to proliferate across a broad spectrum of seemingly unrelated entities. Price impacts are currently modeled via exogenous inverse demand functions. However, in real-world scenarios, only the initial shocks and the final equilibrium asset prices are typically observable, leaving actual asset liquidations largely obscured. This missing data presents significant limitations to calibrating the existing models. To address these challenges, we introduce a novel dual neural network structure that operates in two sequential stages: the first neural network maps initial shocks to predicted asset liquidations, and the second network utilizes these liquidations to derive resultant equilibrium prices. This data-driven approach can capture both linear and non-linear forms without pre-specifying an analytical structure; furthermore, it functions effectively even in the absence of observable liquidation data. Experiments with simulated datasets demonstrate that our model can accurately predict equilibrium asset prices based solely on initial shocks, while revealing a strong alignment between predicted and true liquidations. Our explainable framework contributes to the understanding and modeling of price-mediated contagion and provides valuable insights for financial authorities to construct effective stress tests and regulatory policies.
AB - Financial contagion has been widely recognized as a fundamental risk to the financial system. Particularly potent is price-mediated contagion, wherein forced liquidations by firms depress asset prices and propagate financial stress, enabling crises to proliferate across a broad spectrum of seemingly unrelated entities. Price impacts are currently modeled via exogenous inverse demand functions. However, in real-world scenarios, only the initial shocks and the final equilibrium asset prices are typically observable, leaving actual asset liquidations largely obscured. This missing data presents significant limitations to calibrating the existing models. To address these challenges, we introduce a novel dual neural network structure that operates in two sequential stages: the first neural network maps initial shocks to predicted asset liquidations, and the second network utilizes these liquidations to derive resultant equilibrium prices. This data-driven approach can capture both linear and non-linear forms without pre-specifying an analytical structure; furthermore, it functions effectively even in the absence of observable liquidation data. Experiments with simulated datasets demonstrate that our model can accurately predict equilibrium asset prices based solely on initial shocks, while revealing a strong alignment between predicted and true liquidations. Our explainable framework contributes to the understanding and modeling of price-mediated contagion and provides valuable insights for financial authorities to construct effective stress tests and regulatory policies.
KW - FinTech
KW - asset liquidation
KW - deep learning
KW - explainable machine learning
KW - financial contagion
KW - inverse demand function
UR - http://www.scopus.com/inward/record.url?scp=85179850753&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85179850753&partnerID=8YFLogxK
U2 - 10.1145/3604237.3626887
DO - 10.1145/3604237.3626887
M3 - Conference contribution
AN - SCOPUS:85179850753
T3 - ICAIF 2023 - 4th ACM International Conference on AI in Finance
SP - 108
EP - 115
BT - ICAIF 2023 - 4th ACM International Conference on AI in Finance
T2 - 4th ACM International Conference on AI in Finance, ICAIF 2023
Y2 - 27 November 2023 through 29 November 2023
ER -