Optimal Text-Based Time-Series Indices
This addresses the need for more accurate economic indicators from text data, though it appears incremental as it optimizes existing index construction methods.
The authors tackled the problem of constructing text-based time-series indices to maximize their relation or predictive performance with respect to target variables like inflation, and demonstrated superior performance compared to existing indices using a Wall Street Journal news corpus.
We propose an approach to construct text-based time-series indices in an optimal way--typically, indices that maximize the contemporaneous relation or the predictive performance with respect to a target variable, such as inflation. We illustrate our methodology with a corpus of news articles from the Wall Street Journal by optimizing text-based indices focusing on tracking the VIX index and inflation expectations. Our results highlight the superior performance of our approach compared to existing indices.