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

TL;DR

KANFormer is a deep learning model that predicts the time-to-fill of limit orders by integrating market data, agent actions, and order position, outperforming existing methods in accuracy and interpretability.

Contribution

The paper introduces KANFormer, a novel neural network architecture combining dilated causal convolutions, Transformers, and Kolmogorov-Arnold Networks to improve fill probability predictions in limit order books.

Findings

Outperforms existing models in calibration and discrimination metrics.

Effectively captures order execution patterns using combined market and agent data.

Provides interpretable feature importance insights over time.

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.