Search

Forecasts of the price of crude oil play a significant role in the conduct of monetary policy, especially for commodity producers such as Canada. This article presents a range of recently developed forecasting models that, when pooled together, can generate, on average, more accurate forecasts of the price of oil than the oil futures curve. It also illustrates how policy-makers can evaluate the risks associated with the baseline oil price forecast and how they can determine the causes of past oil price fluctuations.

The substantial variation in the real price of oil since 2003 has renewed interest in the question of how to forecast monthly and quarterly oil prices. There also has been increased interest in the link between financial markets and oil markets, including the question of whether financial market information helps forecast the real price of oil in physical markets.

The U.S. Energy Information Administration regularly publishes short-term forecasts of the price of crude oil.

Notwithstanding a resurgence in research on out-of-sample forecasts of the price of oil in recent years, there is one important approach to forecasting the real price of oil which has not been studied systematically to date.

Canada’s Short-Term Indicator (CSI) is a new model that exploits the information content of 32 indicators to produce daily updates to forecasts of quarterly real GDP growth. The model is a data-intensive, judgment-free approach to short-term forecasting. While CSI’s forecasts at the start of the quarter are not very accurate, the model’s accuracy increases appreciably as more information becomes available. CSI is the latest addition to a wide range of models and information sources that the Bank of Canada uses, combined with expert judgment, to produce its short-term forecasts.

This article examines whether combining forecasts of real GDP from different models can improve forecast accuracy and considers which model-combination methods provide the best performance. In line with previous literature, the authors find that combining forecasts generally improves forecast accuracy relative to various benchmarks. Unlike several previous studies, however, they find that, rather than assigning equal weights to each model, unequal weighting based on the past forecast performance of models tends to improve accuracy when forecasts across models are substantially different.

The formulation of monetary policy at the Bank of Canada relies on the analysis of a broad set of economic information. Greater availability of immediate and detailed information would improve real-time economic decision making. Technological advances have provided an opportunity to exploit “big data” - the vast amount of digital data from business transactions, social media and networked computers. Big data can be a complement to traditional information sources, offering fresh insight for the monitoring of economic activity and inflation.

Forecasts of the quarterly real price of oil are routinely used by international organizations and central banks worldwide in assessing the global and domestic economic outlook, yet little is known about how best to generate such forecasts. Our analysis breaks new ground in several dimensions.

A longstanding finding in the forecasting literature is that averaging forecasts from different models often improves upon forecasts based on a single model, with equal weight averaging working particularly well. This paper analyzes the effects of trimming the set of models prior to averaging.

While the usefulness of factor models has been acknowledged over recent years, little attention has been devoted to the forecasting power of these models for the Japanese economy. In this paper, we aim at assessing the relative performance of factor models over different samples, including the recent financial crisis.