KANFormer for Predicting Fill Probabilities via Survival Analysis in Limit Order Books

2025-12-05

AI Summary

This paper addresses the problem of accurately predicting the time-to-fill for limit orders. Conventional approaches rely solely on order book snapshots and neglect the dynamic behavior of market participants. To overcome this limitation, we propose a survival analysis framework that jointly models market state and participant behavior sequences. Our method incorporates Kolmogorov–Arnold Networks to enhance nonlinear representation learning, integrates dilated causal convolution with a Transformer encoder to capture high-dimensional temporal dependencies, and employs SHAP for post-hoc interpretability. Evaluated on CAC 40 futures data, our model achieves statistically significant improvements over state-of-the-art baselines in both calibration (Brier Score) and discriminative performance (Concordance Index). Results demonstrate its effectiveness, robustness, and interpretability in high-frequency trading environments.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

This paper introduces KANFormer, a novel deep-learning-based model for predicting the time-to-fill of limit orders by leveraging both market- and agent-level information. KANFormer combines a Dilated Causal Convolutional network with a Transformer encoder, enhanced by Kolmogorov-Arnold Networks (KANs), which improve nonlinear approximation. Unlike existing models that rely solely on a series of snapshots of the limit order book, KANFormer integrates the actions of agents related to LOB dynamics and the position of the order in the queue to more effectively capture patterns related to execution likelihood. We evaluate the model using CAC 40 index futures data with labeled orders. The results show that KANFormer outperforms existing works in both calibration (Right-Censored Log-Likelihood, Integrated Brier Score) and discrimination (C-index, time-dependent AUC). We further analyze feature importance over time using SHAP (SHapley Additive exPlanations). Our results highlight the benefits of combining rich market signals with expressive neural architectures to achieve accurate and interpretabl predictions of fill probabilities.

Problem

• Predicts limit order fill times using market and agent data
• Combines dilated CNN, Transformer, and KANs for better accuracy
• Improves execution probability forecasts over snapshot-based models

Innovation

• Combines dilated convolutional network with transformer encoder
• Integrates agent actions and queue position data
• Uses Kolmogorov-Arnold Networks for nonlinear approximation