Monetary Policy & Inflation | US
We use machine learning to convert the Federal Reserve’s (Fed) text-heavy Beige Book into a sentiment score.
This article is only available to Macro Hive subscribers. Sign-up to receive world-class macro analysis with a daily curated newsletter, podcast, original content from award-winning researchers, cross market strategy, equity insights, trade ideas, crypto flow frameworks, academic paper summaries, explanation and analysis of market-moving events, community investor chat room, and more.
Summary
We use machine learning to convert the Federal Reserve’s (Fed) text-heavy Beige Book into a sentiment score. The sentiment (-0.28) of the latest Beige Book report (19 April) showed a slight decrease from the sentiment (-0.26) of the last report (8 March; Chart 1). Notably, the latest report said ‘overall economic activity was little changed in recent weeks’.
Here are the key points from the overall summary of economic activity:
- Nine districts reported either no change or only a slight change in activity this period, while three indicated modest growth.
- Expectations for future growth were mostly unchanged.
- Consumer spending was generally seen as flat to slightly down.
- Auto sales remained steady overall.
- Travel and tourism picked up across much of the country.
- Manufacturing activity, as well as transportation and freight volumes, were widely reported as flat or down.
- Residential real estate sales and new construction activity softened modestly.
- Lending volumes and loan demand generally declined across consumer and business loan types.
- Several Districts noted that banks tightened lending standards amid increased uncertainty and concerns about liquidity.
- Agriculture conditions were mostly unchanged in recent weeks while some softening was reported in energy markets.
Here is a summary of the latest developments from our sentiment index:
- All regional banks, except Cleveland (net-neutral), have a net-negative sentiment (Chart 2). The national summary is marginally positive.
- New York (-0.62, previously: 0.05) has seen the largest drop in sentiment compared to the last report.
- Cleveland (+0.0, previously: -0.42) has seen the largest increase in sentiment compared to the last report.
- New York (-0.62, previously: 0.05), Dallas (-0.56, previously: -0.24), and Boston -0.37, previously: -0.18) are the three districts with the most negative sentiment.
- Overall, sentiment decreased for nine districts and increased for four (including the national summary) – dragging the overall sentiment (-0.28) a touch lower than for the March report (-0.26).
What Is the Macro Hive Beige Book Sentiment Score?
In machine learning, one way to navigate a sea of text and audio-based information is with natural language processing (NLP) techniques. The goal of NLP is to understand textual data to contextualise and extract useful information within it. One application of NLP is sentiment analysis. Sentiment analysis aims to classify whether the opinion expressed in a text is positive or negative (or neutral).
We focus on the Beige Bookand derive a sentiment score by looking at the proportion of positive and negative words in each report. We calculate a raw sentiment score at a district level. Then we aggregate (equally weighted district level average followed by smoothing and detrending) these into an overall sentiment index. We can do this in real-time as soon as the report is released. Charts 4 and 5 show a comparison of our sentiment score to the US ISM PMI and the University of Michigan Consumer Sentiment Index for the US.