Music Playlists Can Predict Market Returns

‘September’ has the highest valence score in 20 out of 40 countries – Photo: Shutterstock

A study published in an upcoming Journal of Financial Economics suggests that short-term stock market performance can be predicted by the types of songs people listen to on the Spotify music streaming service.

Specifically, by analyzing a Spotify statistic called “valence” or positivity to gauge the overall mood of a population, four professors theorize that increased musical sentiment translates to a 1.2 basis point increase in returns, followed five days later by a cut of 1 basis point. .

On an annualized basis, this equates to a 3% increase in stock returns on days when people are listening to upbeat music, followed by a 2.40% decline the following week.

The basis of the study, titled “Music Sentiment and Stock Returns Around the World” – co-authored by Alex Edmans from London Business School, Adrian Fernandez-Perez from Auckland University of Technology, Alexandre Garel from Audencia Business School and Ivan Indriawan from the Department of Finance at Auckland University of Technology – is that many variables affect human sentiment, and because stock traders are human, that sentiment impacts stock returns.

The song with the highest overall valence rating in the US, Canada, UK and much of the EU is Earth Wind & Fire’s Billboard #1 in 1978, with a valence score of 0.982 , according to data maintained by Spotify. Conversely, Legion Inoculant by TOOL ranks last with a valence rating of 0.026. For the 2010s decade alone, Pharrell Williams’ aptly named Happy had the highest score at 0.962, while Post Malone’s Rockstar at 0.129 had the lowest valence score (see table).

Songs from the 2010s with the highest valence rating on SpotifyThe highest valence ratings of songs on Billboard’s Top 100 Songs of the 2010s – Photo: Edmans, Alex

Music as a mood proxy

The many variables that can influence our collective mood include the weather, results of sporting events, geopolitical unrest and Covid-19 restrictions. Although mood can be difficult to quantify, professors believe it is reflected in the choice of music we consume.

“We find that daily index returns are positively correlated with contemporary music sentiment and negatively correlated with sentiment five days prior, suggesting a reversal,” the group wrote. “This result is consistent with the pattern we observe at the weekly frequency and suggests that mood swings, as reflected in musical sentiment, drive stock price variations.”

Moreover, they find that in the US – where equity trading is less restricted than in most other markets – the rally is happening faster, after three days of positive sentiment gains.

Covid-19 restrictions influence mood

This is evident in the Covid-19 related short selling bans and trading volume restrictions implemented in some countries but not others in March 2020, which exacerbated the effect. Two countries introduced such restrictions on stock trading shortly after Covid-19 was declared a global pandemic and stock returns have seen an above-average correlation with music sentiment.

In France, where a short-selling ban was instituted on March 17, 2020, and when Australia capped trading volume, a one standard deviation increase in music sentiment was followed by a 33% increase, 6 basis points in contemporary returns, followed by an 89.2 basis point drop in future returns.

“In sum, the effect of musical sentiment on market returns is significantly stronger when a country’s stock market is subject to arbitrage limits,” the professors surmised.

Songs from the 2010s with the lowest Valence rating on SpotifyThe lowest valence ratings of songs on Billboard’s Top 100 Songs of the 2010s – Photo: Edmans, Alex

UCITS flows affected

Capital flows from mutual funds are also correlated with musical sentiment, the professors found. For example, based on an average fund size of $976m (£727.7m), a one standard deviation increase in music sentiment resulted in a weekly fund inflow of $29,000, or $1.5 million on an annualized basis. Conversely, the same-sized fund experienced an outflow of $31,000 the following week, or $1.6 million on an annualized basis.

For flight-to-safety government bonds, the results were limited. Although the study found that a one standard deviation increase in music sentiment led to a 0.01 basis point decrease in bond-linked fund returns or an annual decline of 0.5% – significant being given that the average bond fund return is 2.2% per year – the study found no inverse relationship for future bond fund returns.

In conclusion, the professors believe that musical sentiment, as measured by Spotify’s valence metric, can be used as an indicator of the general mood of a population, and is therefore predictive of its short-term asset prices. .

Read more:

small tree in hand
Figurines of miners digging the ground to discover big golden bitcoins

Rate this article

Ready to start?


The difference between trading assets and CFDs
The main difference between trading CFDs and trading assets, such as commodities and stocks, is that you do not own the underlying asset when trading a CFD.
You can always profit if the market moves in your favor or suffer a loss if it moves against you. However, with traditional trading, you enter into a contract to exchange legal ownership of individual stocks or commodities for cash, and you own them until you sell them again.
CFDs are leveraged products, which means that you only have to deposit a percentage of the total value of the CFD transaction to open a position. But with traditional trading, you buy the assets for the full amount. In the UK there is no stamp duty on CFD trading, but there is when you buy shares, for example.
CFDs attract overnight costs to hold trades (unless you are using 1-1 leverage), which makes them more suitable for short-term trading opportunities. Stocks and commodities are more normally bought and held longer. You might also pay a commission or brokerage fee when buying and selling assets directly and you would need a place to store them securely.

Capital Com is an execution-only service provider. The material provided on this website is provided for informational purposes only and should not be construed as investment advice. Any opinion that may be provided on this page does not constitute a recommendation by Capital Com or its agents. We make no representations or warranties as to the accuracy or completeness of the information provided on this page. If you rely on any information on this page, you do so entirely at your own risk.

George L. Hernandez