KAN vs LSTM Performance in Time Series Forecasting
This is an incremental comparison for financial forecasting practitioners, confirming LSTM's established dominance in accuracy-critical time series applications.
This paper compared Kolmogorov-Arnold Networks (KAN) and Long Short-Term Memory networks (LSTM) for stock price forecasting, finding that LSTM significantly outperformed KAN in accuracy across all tested horizons, with KAN showing higher error rates but computational efficiency advantages.
This paper compares Kolmogorov-Arnold Networks (KAN) and Long Short-Term Memory networks (LSTM) for forecasting non-deterministic stock price data, evaluating predictive accuracy versus interpretability trade-offs using Root Mean Square Error (RMSE).LSTM demonstrates substantial superiority across all tested prediction horizons, confirming their established effectiveness for sequential data modelling. Standard KAN, while offering theoretical interpretability through the Kolmogorov-Arnold representation theorem, exhibits significantly higher error rates and limited practical applicability for time series forecasting. The results confirm LSTM dominance in accuracy-critical time series applications while identifying computational efficiency as KANs' primary advantage in resource-constrained scenarios where accuracy requirements are less stringent. The findings support LSTM adoption for practical financial forecasting while suggesting that continued research into specialised KAN architectures may yield future improvements.