In this Intelligence report, we highlight key findings from a backtest that was carried out by an alternative data provider earlier this year on their proprietary US corn production forecasts. We also compare the vendor's results to those observed by a competing US corn yield forecaster.

Whether you call it web scraping, web crawling or spidering, programmatic data access and extraction belongs to the realm of technologies that have outpaced developments within the world of legislation. In the following piece, we provide an introduction to legal theories and concepts that have proven relevant to web scraping activities, as well as some widely accepted guidelines for good bot behaviour.

Empirical evidence suggests that the financial performance of companies is inversely correlated with employee turnover. More interestingly, we look into this subject in more depth by assessing whether this relationship is exacerbated or dampened across particular industries or level of employee seniority. We also outline several alternative data providers we believe are best placed to provide such predictive turnover analytics.

Ahead of the 2018 holiday season we look back to Black Friday 2017 and perform a proprietary analysis of how investors can utilise advertising and clickstream datasets to predict the performance of retailers over this period. In particular, we focus on three large US retailers: Walmart, Target, and Kohl’s.

We recently discussed how the American Customer Satisfaction Index (ASCI) generates superior returns at a lower systematic risk. In this piece, we discuss Net Promoter Scores (NPS) – a popular measurement of customer loyalty – and whether it is an appropriate metric for investment managers aiming to predict company financial performance.

We discuss the key regulatory issues concerning the collection, processing and usage of geolocation data. Starting with the definition of geolocation data as ‘personal data’, we draw attention to several cautionary tales of data misappropriation or privacy leakage, before discussing best practices according to GDPR, as well as the logistical and legal challenges associated with data anonymization. We also draw attention to several future policy developments that should be on the radar of any informed user of geolocation data.

We explore the idea that companies with higher levels of customer satisfaction generate superior returns at lower systematic risk based on two research studies, one of which analyses the relationship between customer satisfaction and stock market returns over a 15-year period. We highlight key findings, illustrating the stock-specific use cases for customer satisfaction data. We also highlight a number of alternative data providers who offer measures of customer satisfaction.

In the first part of this series, we introduced the ways in which location information (ideally coordinate-based) is generated and subsequently made available to third parties. In the second part, we provide an overview of the technologies and challenges associated with contextualizing raw location data.

We discuss whether art auction prices (and in particular Sotheby’s stock price) is indicative of global overconfidence, or whether such data points add little, if any, value to macro investors. We also identify four relevant alternative data sources that can be leveraged by readers interested in incorporating such data into their decision-making processes.

We outline how hospital purchase order data can be used by investors to track medical device companies using three case studies provided by a Neudata-listed alternative data provider. Specifically, we look at how purchase order data could provide value for investors across three medical device companies: Penumbra (PEN), Intersect ENT (XENT), and Zimmer Biomet (ZBH). We also share our views on the comparative advantages and disadvantages of different providers offering this type of data.