Interval-valued time series forecasting using a novel hybrid HoltI and MSVR model

- Extending the “linear and nonlinear” framework to the scenario of ITS forecasting.
- Proposing a novel prediction method for interval-valued time series.
- The experimental analysis is based on one- and multi-step-ahead interval forecasts.
- The proposed method is justified with statistical and economic criteria.
- HoltI-MSVR is a promising method for interval-valued time series forecasting.

In view of the importance of interval-valued time series (ITS) modeling and forecasting, and the less research efforts made before, this study proposes an hybrid modeling framework combining interval Holt's exponential smoothing method (HoltI) and multi-output support vector regression (MSVR) for ITS forecasting. Following the philosophy of well-established hybrid “linear and nonlinear” modeling framework, HoltI and MSVR are committed to capture the linear and nonlinear patterns hidden in ITS, respectively. Different from the previous studies considering to model the highs and lows of intervals separately, the proposed hybrid method (termed as HoltI-MSVR) is used to model and forecast the daily highs and lows of ITS simultaneously, taking into account the possible interrelations between the bounds. Three ITS datasets extracted from finance market and energy market are used to compare the prediction performance of the HoltI-MSVR with five selected competitors. The experimental results are judged on the basis of statistical criteria, i.e., the goodness of forecast measure and the accuracy compared to competing forecasts test, and economic criteria, i.e., the returns obtained from a simple trading strategy based on the interval forecasts. The results obtained suggest that the proposed HoltI-MSVR is a promising alternative for ITS forecasting.