Currently, Amazon relies on third parties for transportation marketplace rate forecasts, despite the poor quality and lack of interpretability of these forecasts. While transportation marketplace rates are typically very challenging to forecast accurately, we have developed a novel signature-based statistical technique to address these challenges and built a predictive and adaptive model to forecast marketplace rates. This novel technique is based on two key properties of the signature transform. The first is its universal nonlinearity which linearizes the feature space and hence translates the forecasting problem into a linear regression analysis; the second is the signature kernel which allows for comparing computationally efficiently similarities between time series data. Combined, these properties allow for efficient feature generation and more precise identification of seasonality and regime switching in the forecasting process. Preliminary result by the model shows that this new technique leads to far superior forecast accuracy versus commercially available industry models with better interpretability, even during the period of Covid-19 and with the sudden onset of the Ukraine war.

翻译：目前，亚马逊依赖于第三方进行交通市场费率预测，尽管这些预测质量低下且缺乏可解释性。尽管交通市场费率通常极难准确预测，我们开发了一种基于签名的新型统计技术来应对这些挑战，并构建了一个可预测且自适应的模型用于市场费率预测。这项新技术基于签名变换的两个关键特性：其一，它的通用非线性特性能够线性化特征空间，从而将预测问题转化为线性回归分析；其二，签名核能够高效计算时间序列数据之间的相似性。综合这些特性，该技术能够实现高效的特征生成，并在预测过程中更精确地识别季节性和机制转换。模型的初步结果表明，即使在新冠疫情期间以及乌克兰战争突然爆发的情况下，这项新技术相较于商用行业模型，不仅具有更好的可解释性，而且预测准确性也显著更优。