Improved stock forecasting with adaptive volatility and noise reduction
A decomposition-integration framework coupling singular spectrum analysis with a volatility-adaptive LSTM for stock price forecasting
Computational Engineering, Finance, and ScienceMachine Learning
Summary
Stock prices are hard to predict because their ups and downs happen at different speeds and with lots of random noise. The authors created a new method that breaks down the price data into parts based on their speed, cleans up the noisy parts, and predicts future prices using a smart memory system that adjusts when the market is more or less volatile. They tested this method on big US and Chinese market data and found it made predictions more accurate than common alternatives. This approach also shows potential for helping make money decisions by reducing errors in forecasts.
What this means in practice
- •For quantitative traders: Use the volatility-adaptive forecasting model to improve the accuracy of stock price predictions and enhance trading strategies with dynamic risk sensitivity.
- •For financial risk managers: Incorporate the conditional volatility modulation into risk assessment tools to better capture market fluctuations and adjust risk estimates dynamically.
Authors
Xin-Rui Lu, Da-Qing Zhang
Abstract
Financial time series exhibit multi-scale, high-noise, and non-stationary volatility dynamics. Decomposition--integration frameworks built on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) have advanced this field, yet existing CEEMDAN hybrids remain unstable: high-frequency mode mixing contaminates downstream predictors, and the heterogeneous volatility of decomposed components is not matched by any volatility-adaptive mechanism. To address these gaps, this paper proposes CEEMDAN-SE-SSA-VMGL. CEEMDAN adaptively decomposes the original series, and sample-entropy-driven K-means clustering groups the intrinsic mode functions into high-, mid-, and low-frequency and residual components. Singular spectrum analysis (SSA) is then applied to the high-frequency group, whose singular-value decomposition of the trajectory matrix and principal-component reconstruction decouple intertwined pseudo-oscillatory modes and alleviate mode mixing. We further design a plug-and-play robust LSTM variant, the volatility-modulated GARCH-LSTM (VMGL), which embeds a differentiable GARCH(1,1) layer inside the LSTM cell as a risk gate; the estimated conditional volatility multiplicatively scales the forget-gate activation, letting memory decay adapt to the instantaneous volatility while remaining fully end-to-end trainable. Component predictions are linearly combined. On five US and Chinese financial series (CSI 300, CSI 500, AAPL, GOOGL, S&P 500), the proposed model is compared with eleven benchmark architectures, lowering the forecasting error by 9% to 24% relative to the best benchmark and by 60% to 70% relative to a standard LSTM. Diebold--Mariano and model-confidence-set (MCS) tests confirm the statistical significance and stability of the gains, spectral analyses verify the SSA denoising efficacy, and backtesting demonstrates the framework's economic utility.