Stock-bond Yield Correlation Analysis based on Natural Language Processing

U.S. Treasury yield rates are the most important reference for global asset pricing and usually affect the stock market. Therefore, research on the correlation between China's core asset valuation and Treasury yield rates is becoming more and more important. The current statistical measurement methods have shortcomings such as the short period of market variables, low frequency, and inability to observe indicators of different countries in real-time. News, as information that reflects the public's attention and cognition, directly affects investors' stock trading behavior in the short term and has timeliness. We construct Correlation Strength by News (CSN) index for the first time to measure the correlation strength between treasury yield rates and the stock market from the perspective of media attention. The proposed method effectively solves the problem of the traditional method, such as the lack of data update timeliness and forecasting effectiveness. The capability of the index as an alternative variable of the correlation degree between the treasury yield rates and the stock market is verified.

I. Introduction

10-Year U.S. Treasury yield rates are the most important weathervane in the world and the most important reference for asset pricing. At the beginning of 2021, driven by inflation expectations, 10-Year U.S. Treasury yield rates began to soar, once exceeding 1.7%, which triggered panic in the financial market and brought huge pressure on the stock market. As financial assets become more diversified, investors will have more options to allocate funds and transfer portfolio weights between riskier and safer assets to cope with a potential loss risk. As the stock is more closely related to the company's performance, it’s regarded as a higher-risk asset with higher volatility, although it may provide investors with higher potential profits. On the contrary, as the bonds are guaranteed to be paid by the government, it’s considered a lower-risk choice, which provides a safety net for investors. To avoid economic losses, investors will put a certain proportion of money into the bond market to minimize their potential losses. Therefore, the research on the stock-bond correlation is of vital importance. From the perspective of investors, the study can help them avoid "putting all the eggs in one basket" through portfolio diversification. From the perspective of policymakers, the study can help them monitor the financial system more effectively, determine the market's view of inflation level and economic activities, and thus implement appropriate monetary policies to respond to inflation and growth expectations.