DAILY CRUDE OIL PRICE FORECASTING MODEL USING ARIMA, GENERALIZED AUTOREGRESSIVE CONDITIONAL HETEROSCEDASTIC AND SUPPORT VECTOR MACHINES

Abstract

Crude oil price forecasting is gaining increased interest globally. This interest is due mainly to the economic value attached to the product. For this reason, new forecasting methods are proposed in the literature. This paper proposes a novel technique for forecasting crude oil price based on Support Vector Machines (SVM). The study adopts the data on crude oil price of West Texas Intermediate (WTI) for its experimental purposes. This is because many studies have previously used this same data and it will afford a common basis for assessment. To evaluate the performance of the model, the study employs two measures, RMSE and MAE. These are used to compare the performance of the proposed technique and that of ARIMA and GARCH methods for the most efficient in crude oil price forecasting. The results reveal that the proposed method outperforms the other two in terms of forecast accuracy while it achieved a forecast error of 0.8684 that of ARIMA and GARCH were 0.9856 and 1.0134 respectively judging by their RMSE.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 70 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.