Alternative Data News and Insight

The rate of workforce resignations has steadily increased since the 2007/08 financial crisis. Predicting attrition has never been more critical - excessive turnover can harm business performance as it impedes productivity, increases operational costs and reduces company morale. In this report, we summarise a study that identifies the key drivers of attrition using alternative data sources.

We summarise a recent academic work that investigated how emotions expressed in news can help predict changes in European bond yield spreads.

Chinese retail investors are well-known for their speculative and irrational behavior, and their informational role has often been perceived as “questionable.” We highlight the findings of a research paper that examines the role of retail investors in information discovery and dissemination based on NLP-enabled text analysis.

The following research paper takes a three-pronged approach to tracing the emergence of new technologies within firms and industries: patent filings, earnings calls, and geolocated, role-specific hiring activity metrics.

Most alternative data users will be familiar with applications of NLP-based sentiment analysis on corporate earnings call transcripts, but few are acquainted with sentiment analysis on the audio itself. Below, we review literature that showcase how audio analysis can be used to gauge distress through the tone of C-suite executives in corporate earnings calls.

We summarise a recent paper on the use of alternative data in investment management, published by Gene Ekster and Petter Kolm. Their paper discusses the alternative data ecosystem, use cases, challenges, and methodologies for the valuation of alternative datasets.

We summarise a study that investigated whether a company’s Form 5500, and the metadata reported within the disclosure, provides equity investors with an information advantage.

The Food and Drug Administration (FDA) can take months to identify, investigate and issue product recalls, often after enough people have gotten sick to trigger negative press. US Health Departments are already using data from Twitter, Yelp, and Google to monitor foodborne illnesses – suggesting that many alternative data sources could provide early signals for product recalls. In this report, we review a public health study that uses a trained NLP engine to predict FDA product recalls using Amazon.com reviews.

We summarise a recent academic work that investigated REITs’ ability to provide data on ESG compliance, and how that transparency impacts their overall ESG performance, stock returns, and investors’ willingness to pay a premium.

We summarize the findings of a whitepaper that analyses how the use of alternative data can help determine whether an equity’s cybersecurity investments reduce their vulnerability to future attacks.