How good are analyst forecasts of oil prices?

摘要

Even though there is a wide consensus that having good oil price forecasts is very valuable for many agents in the economy, results have not been fully satisfactory and there is an ongoing effort to improve their accuracy. Research has explored many different modeling approaches including time series, regressions, and artificial intelligence, among others. Also, many different sources of input data have been used like spot and futures prices, product spreads, and micro and macro variables.This paper explores how useful analyst expected price data are for forecasting when appropriate measures are taken to account for their sparse nature and high volatility. It proposes a multifactor stochastic pricing model, with time-varying risk premiums calibrated with filtered futures and analyst forecasts using a Kalman Filter.The forecasting model is applied to ten years of oil prices and analyst forecasts, from NYMEX and Bloomberg, respectively. Results are very encouraging showing that the model forecasts are much better than the no-change forecasts, commonly used as a benchmark, and better than those from the widely used Bloomberg's Consensus Expected Price Model. We conclude that analyst forecasts are a valuable source of input data that should be considered in future forecasting models.