Using Online Activity and Consumer Data as Factors in Equity Selection
Summary
This article explains how alternative internet and transaction data can supplement traditional equity factors. A typical fund process first defines a stock universe, filters it using industry and financial measures, scores candidates with financial and market factors, then assigns constituents and weights. Big data approaches add signals such as search volume, online discussion and news engagement, e-commerce trends, and card spending. The article describes a consumer data example in which spending trends are used to estimate industry growth, pricing, and supply-demand conditions, then score stocks within related industries.
It also outlines search, investor-platform attention, news sentiment, and payment-data factors used by several Chinese index or fund examples. These descriptions illustrate possible data sources and factor construction, but the article supplies no quantified evaluation of predictive power or implementation costs. It notes that the cited big data funds had not met initial expectations and characterizes the field’s use as cautious and exploratory. Alternative data therefore appears as an addition to multifactor models, not established proof of an independent or reliable edge.
Key ideas
- Alternative data can supplement financial and market factors in a stock-ranking model.
- Potential signals include search activity, online attention, news tone, e-commerce trends, and payment statistics.
- Consumer data can be aggregated into industry indicators and used to score companies in related sectors.
- The article reports that cited funds had not met their initial expectations and offers no detailed performance tests.
- Natural-language and machine-learning methods may be needed to process some data sources.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.