The forecast of time series in financial applications is difficult to perform as time series forecasting is nonlinear in nature, seasonal, and has structural variability. Stock price series tend to follow a lot of nonlinear dynamics, which undermines the power of single-model approaches. Hybrid decomposition-based models have attracted increasing interest in order to gain accuracy by separating heterogeneous features from one another. In this work, we present a hybrid forecasting methodology that incorporates STD decomposition with RBFNN (Radial Basis Function Neural Network). The time series is decomposed, where trend, seasonal, and dispersion components are separately modeled using RBFNN with Gaussian basis functions. The predicted feature sets are then recombined to construct a forecast, to be evaluated with weekly Tesla stock price data and standard accuracy performance metrics. The experimental analysis of weekly Tesla stock price data presents that the STD-RBFNN structure results in lower forecast errors, compared to the comparison hybrid model discussed in this paper. The improvement seems to be realized by decomposing the original series into components before learning non-linearly, and then by reconstructing the final forecast from component-wise predictions. But this empirical work remains narrow to a single-asset case type and the benchmark set here. The proposed framework is therefore considered to be a prospective hybrid forecasting design that needs validation across additional assets and forecasting models to achieve wider generalizability.
Abdullah et al. (Thu,) studied this question.