Hybrid Time Series Forecasting Models: An In-depth Evaluation Across Financial and Climatic Indicators

This work extensively evaluates time series forecasting models, focusing on individual algorithms and hybrid combinations. The study explores the forecasting capabilities across five diverse time series, comprising financial indicators and climatic variables. The models considered include autoregressive integrated moving average (ARIMA), exponential smoothing (ES), singular spectrum analysis (SSA), and Long Short-Term Memory (LSTM), along with hybrid variations. The hybrid time series models demonstrate superior performance by enhancing forecasting accuracy in most of the scenarios. The models SSA-LSTM-LSTM, SSA-R-LSTM, and SSA-ARIMA-LSTM perform well for the stock exchange rate, NASDAQ Composite Index, and solar radiation data, respectively. These hybrid approaches leverage the strengths of diverse algorithms, showcasing adaptability, robustness, and flexibility in handling various time series patterns. A short-term daily forecasting scenario provides insights into short-term predictive capabilities, highlighting the effectiveness of hybrid models in capturing rapid fluctuations. The study contributes valuable insights for researchers and practitioners seeking optimal time series forecasting strategies based on specific data characteristics and forecasting requirements.