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 (-0.29) of the latest Beige Book report (31 May) showed a slight decrease from the sentiment (-0.28) of the last report (19 April), putting it in line with the GFC sentiment lows in July 2009 (Chart 1). This is in line with the Fed’s take on the economy: ‘economic activity was little changed overall in April and early May.’
Here are the key points from the overall summary of economic activity:
- Four Districts reported small increases in economic activity, while six reported no change, and two reported slight-to-moderate declines.
- Expectations for future growth deteriorated a little.
- Consumer expenditures were steady or higher in most districts.
- Education and healthcare organizations saw steady activity on balance.
- Manufacturing activity was flat to up in most districts.
- Demand for transportation services was down, especially in trucking, where contacts reported there was a ‘freight recession.’
- Residential real estate activity picked up in most districts despite continued low inventories of homes for sale.
- Outlooks for farm income fell in most districts.
- Financial conditions were stable or somewhat tighter in most districts.
- Contacts in several districts noted a rise in consumer loan delinquencies.
- There has been an increased demand for social services, including food and housing as high inflation and the end of Covid-19 benefits continue to stress the budgets of low- and moderate-income households.
Here is a summary of the latest developments from our sentiment index:
- All regional banks, except Minneapolis (+0.12) and Philadelphia (net-neutral), have a net-negative sentiment (Chart 2). The national summary is also net negative (-0.11).
- Cleveland (-0.58, previously: net-neutral) has seen the largest drop in sentiment compared to the last report.
- Philadelphia (net-neutral, previously: -0.33) has seen the largest increase in sentiment compared to the last report.
- St Louis (-0.64, previously: -0.26), Cleveland (-0.58, previously: net-neutral), and Atlanta (-0.45, previously: -0.29) are the three districts with the most negative sentiment.
- Overall, sentiment decreased for six districts and increased for seven (including the national summary). The overall sentiment was dragged down to -0.29, a touch lower than for the April report (-0.28), mostly due to the outsized decreases in sentiment for Cleveland and St Louis relative to the rest of the districts.
- The touch lower in sentiment corresponds with drops in the Manufacturing PMI and the University of Michigan Consumer Sentiment Index in May (Charts 4 and 5).
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.