Temporal Kolmogorov-Arnold Networks (T-KAN) for High-Frequency Limit Order Book Forecasting: Efficiency, Interpretability, and Alpha Decay

TL;DR

This paper introduces Temporal Kolmogorov-Arnold Networks (T-KAN), a novel model for high-frequency limit order book forecasting that improves accuracy, interpretability, and efficiency, outperforming traditional models like DeepLOB especially over longer horizons.

Contribution

The paper proposes T-KAN, replacing fixed linear weights with learnable B-spline activations, enhancing market signal learning and model interpretability in high-frequency trading environments.

Findings

19.1% relative improvement in F1-score at horizon k=100

132.48% return compared to DeepLOB under transaction costs

Model is optimized for low-latency FPGA implementation

Abstract

High-Frequency trading (HFT) environments are characterised by large volumes of limit order book (LOB) data, which is notoriously noisy and non-linear. Alpha decay represents a significant challenge, with traditional models such as DeepLOB losing predictive power as the time horizon (k) increases. In this paper, using data from the FI-2010 dataset, we introduce Temporal Kolmogorov-Arnold Networks (T-KAN) to replace the fixed, linear weights of standard LSTMs with learnable B-spline activation functions. This allows the model to learn the 'shape' of market signals as opposed to just their magnitude. This resulted in a 19.1% relative improvement in the F1-score at the k = 100 horizon. The efficacy of T-KAN networks cannot be understated, producing a 132.48% return compared to the -82.76% DeepLOB drawdown under 1.0 bps transaction costs. In addition to this, the T-KAN model proves quite interpretable, with the 'dead-zones' being clearly visible in the splines. The T-KAN architecture is also uniquely optimized for low-latency FPGA implementation via High level Synthesis (HLS). The code for the experiments in this project can be found at https://github.com/AhmadMak/Temporal-Kolmogorov-Arnold-Networks-T-KAN-for-High-Frequency-Limit-Order-Book-Forecasting.