Mining Credit Card Data for Stock Returns

Consumer Spending and the Cross Section of Stock Returns

• Tarun Gupta, Edward Leung, and Viorel Roscovan
• Journal of Portfolio Management, 2022
• A version of this paper can be found here
• Want to read our summaries of academic finance papers? Check out our Academic Research Insight category

What are the Research Questions?

In this article, the authors explore an alternative measure of consumer demand from a unique dataset of individual credit and debit card daily transactions ( available one week after the transaction was made on average) from January 2013 to December 2019.

They ask the following:

1. Can more timely information such as daily transactions information on sales predict future earnings surprises?
2. Can more timely information such as daily transactions information on sales predict future stock returns?
3. Is there value added from the consumer transactions signal on top of the common drivers of risk and return, such as size, value, momentum, and profitability factors?

What are the Academic Insights?

1. YES, transactions data positively predict various measures of a company’s future earnings surprises over the next three quarters. This predictive power remains strong in both large- and small-cap universes of consumer discretionary firms in the sample and is robust to the type of transactions data considered (credit, debit, or both) although the relationship is stronger in the small-cap universe in which informational asymmetries are more pronounced.

2. YES- investors can gain substantial returns by trading on signals constructed from consumer transaction data. Specifically, a simple long–short trading strategy that takes long–short positions in the top/bottom tercile of stocks ranked on our transactions-level signal generates statistically and economically significant returns of 16% per annum net of transaction costs and after controlling for the common sources of systematic factor returns.

3. The consumer transactions long-short portfolio has some positive exposure to price momentum and negative exposure to value.

Why does it matter?

This article provides some initial evidence that valuable information can be extracted from an alternative
higher-frequency data source, allowing asset managers to construct alternative factors that would provide them with an edge in identifying trading opportunities. An open question is if/when this will be arbitraged.

The Most Important Chart from the Paper:

Abstract

Using a unique dataset of individual transactions-level data for a universe of US consumer facing stocks, we examine the information content of consumer credit and debit card spending in explaining future stock returns. Our analysis shows that consumer spending data positively predict various measures of a company’s future earnings surprises up to three quarters in the future. This predictive power remains strong in both large- and smallcap universes of consumer discretionary firms in our sample and is robust to the type of transactions data considered (credit card, debit card, or both), although the relationship is stronger in the small-cap universe where informational asymmetries are more pronounced.
Based on this empirical observation, we build a simple long–short strategy that takes long– short positions in the top/bottom tercile of stocks ranked on our real-time sales signal.
The strategy generates statistically and economically significant returns of 16% per annum net of transaction costs and after controlling for the common sources of systematic factor returns. A simple optimization exercise to form (tangency) mean–variance-efficient portfolios of factors leads to an optimal factor allocation that assigns almost 50% weight to our long–short portfolio. Our results suggest that consumer transaction level data can serve as a more accurate and persistent signal of a firm’s growth potential and future returns.