Optimal Text-Based Time-Series Indices

TL;DR

This paper introduces an optimal method for constructing text-based time-series indices that improve tracking and prediction of financial variables like the VIX and inflation, outperforming existing indices.

Contribution

It presents a novel approach to optimize text-based indices for better correlation and prediction of economic indicators using news data.

Findings

Optimized indices outperform existing ones in tracking the VIX.

Optimized indices better predict inflation expectations.

Method demonstrates significant performance improvements.

Abstract

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.