Exogenous Data in Forecasting: FARM -- An Approach for Relevance Evaluation

Exogenous data is believed to play a key role for increasing forecasting accuracy. For an appropriate selection, a throughout relevance analysis is a fundamental first step, starting from the exogenous data similarity with the reference time series. Inspired by existing metrics for time series similarity, we introduce a new approach named FARM - Forward Angular Relevance Measure, able to effectively deal with real-time data streams. Our forward method relies on an angular feature that compares changes in subsequent data points to align time-warped series in an efficient way. The proposed algorithm combines local and global measures to provide a balanced relevance measure. This results in considering also partial, intermediate matches as relevant indicators for exogenous data series significance. As a first validation step, we present the application of our FARM approach to both synthetic but representative signals and real-world time series recordings. While demonstrating the improved capabilities with respect to existing approaches, we also discuss existing constraints and limitations of our idea.