Hybrid Kolmogorov-Arnold Network and XGBoost Framework for Week-Ahead Price Forecasting in Australia's National Electricity Market

TL;DR

This paper introduces a hybrid KAN+XGBoost framework that effectively captures both long-term dependencies and short-term fluctuations for week-ahead electricity price forecasting in Australia's volatile NEM market.

Contribution

It proposes a novel hybrid model combining KAN and XGBoost, improving forecasting accuracy over existing methods in a complex electricity market.

Findings

The hybrid model reduces MAE by approximately 12% compared to XGBoost.

It outperforms benchmark methods like SARIMAX and LSTM.

The approach is effective in highly dynamic electricity markets.

Abstract

Accurate electricity price forecasting (EPF) is essential for market participants to support operational planning and risk management, yet remains challenging due to strong volatility, nonlinear dynamics, and frequent extreme price spikes. These challenges are particularly pronounced in the Australian National Electricity Market (NEM), where high renewable penetration further increases uncertainty. This paper investigates week-ahead electricity price forecasting and proposes a hybrid KAN+XGBoost framework that integrates Kolmogorov-Arnold Networks (KAN) with tree-based learning. The proposed approach combines the global nonlinear representation capability of KAN with the local robustness of XGBoost to capture both long-term dependencies and short-term price fluctuations. Experiments are conducted on real-world NEM data using an expanding window evaluation strategy. The results demonstrate that the proposed model outperforms benchmark methods, including SARIMAX, Long Short-Term Memory (LSTM), standalone KAN, and XGBoost, reducing MAE by approximately 12% compared to XGBoost and by over 50% compared to a naive baseline. The results suggest that hybrid learning strategies provide an effective and robust solution for electricity price forecasting in highly dynamic electricity markets.