Increasingly commodities have become an asset class in a process called financialization. Many institutional investors, looking for ways to expand their diversification opportunities, are holding positions in a commodity futures index and use them as a performance benchmark. Thus, institutional commodity holdings in commodities has expanded significantly.

In this paper we estimate the risk premium of a commodity index using analyst’s forecasts and futures prices of each of the commodities included in the index. We estimate futures and expected spot price curves using a no-arbitrage multifactor stochastic pricing model and a Kalman Filter. The model includes time-varying risk premia thus allowing for the exploration of macro variables that could explain their time variation for each family of commodities.

The proposed model has already shown to be effective for single commodities, such as oil and copper, but this paper extends its use to analyze indices of the four main commodity sectors: energy, industrial metals, precious metals and agriculture, as well as a global portfolio that mimics the S&P GSCI Index. This allows for a better understanding of how some macro variables affect different commodity sectors providing useful information for institutional investors of a commodity index.

在一个被称为金融化的过程中，商品越来越多地成为一种资产类别。许多机构投资者正在寻找扩大多元化机会的方法，持有商品期货指数的头寸并将其用作业绩基准。因此，大宗商品的机构大宗商品持有量显着增加。

在本文中，我们使用分析师的预测和指数中包含的每种商品的期货价格来估计商品指数的风险溢价。我们使用无套利多因素随机定价模型和卡尔曼滤波器估计期货和预期现货价格曲线。该模型包括随时间变化的风险溢价，因此可以探索宏观变量，这些变量可以解释每个商品系列的时间变化。

所提出的模型已经证明对石油和铜等单一商品有效，但本文将其用途扩展到分析四个主要商品部门的指数：能源、工业金属、贵金属和农业，以及全球模拟标准普尔 GSCI 指数的投资组合。这有助于更好地了解一些宏观变量如何影响不同的商品部门，为商品指数的机构投资者提供有用的信息。