← Back to all news
arXiv Machine Learning By Ahmad Makinde

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

Read the original on arXiv Machine Learning →

The paper introduces Temporal Kolmogorov‑Arnold Networks (T‑KAN) for forecasting high‑frequency limit order book data, replacing fixed linear weights in LSTMs with learnable B‑spline activation functions. This approach captures the shape of market signals, yielding a 19.1% relative improvement in F1‑score at a 100‑step horizon and a 132.48% return versus a -82.76% drawdown for DeepLOB under 1.0 bps transaction costs. T‑KAN also offers interpretability through visible dead‑zones in the splines and is optimized for low‑latency FPGA deployment via High‑Level Synthesis.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Jul 7

KAN vs LSTM Performance in Time Series Forecasting

arXiv:2511. 18613v2 Announce Type: replace-cross Abstract: This study presents a controlled comparison of baseline Kolmogorov-Arnold Networks (KAN), implemented via PyKAN, and Long Short-Term Memory (LSTM) networks for the forecasting of stochastic, non-stationary financial time series.

By Tabish Ali Rather, S M Mahmudul Hasan Joy, Nadezda Sukhorukova, Federico Frascoli
benchmarkssafety
More like this →
arXiv Machine Learning
Aug 4

An Embedded RISC-V Evaluation of Kolmogorov--Arnold Networks in Hard-Constrained Recurrent Physics-Informed Models

arXiv:2608. 00737v1 Announce Type: new Abstract: Hard-constrained recurrent physics-informed networks (HRPINNs) embed known dynamics inside a recurrent numerical integrator and restrict a neural branch to learning only the residual dynamics that the first-principles model does not capture.

By Enzo Nicolas Spotorno, Josafat Leal Filho
efficiency
More like this →
arXiv Machine Learning
5d ago

Aurora-X: Built for Extreme Time Series Forecasting

Aurora‑X is a billion‑parameter time‑series foundation model designed for extreme forecasting tasks. It employs a progressive curriculum that starts with channel‑independent pretraining, then adds cross‑variable dependencies, variable context and horizon lengths, and optional future covariates during mid‑training. A variable‑resolution post‑training stage allows adjustable temporal spans per token at inference, while a pattern‑guided mixture‑of‑experts expands capacity through sparse activation and expert specialization. An implicit quantile network head predicts arbitrary quantiles, enhancing probabilistic forecasting flexibility. Experiments on GIFT‑Eval, TIME, FEV‑Bench, TFB, and DAG‑Bench show state‑of‑the‑art performance against both pretrained TSFMs and task‑specific supervised models.

By Xingjian Wu, Chenjuan Guo, Xiangfei Qiu, Zhigang Hu, Hanyin Cheng, Peng Chen, Yang Shu, Jilin Hu, Bin Yang
benchmarks
More like this →