| September 21, 2016
We show that supply-chain and competitive landscape information can help create more scalable portfolios from infrequent or sparse signals.
In this research, we use an earnings sentiment indicator as a signal, constructed using RavenPack Data. We find value in propagating the signal from the source companies to their suppliers and competitors.
Here are some of the highlights
Uncovering business relationships among companies can help build
profitable investment strategies
. No company operates in isolation; they are all part of an ecosystem consisting of suppliers, competitors, customers, and partners, also known as economically-linked companies. Understanding a company’s business relationships informs investors about their business opportunities and risk exposure. For example, looking at the sentiment of one company can tell you how the market might perceive its suppliers or competitors, and this can be exploited in order to get larger and more scalable investment portfolios.
Portfolio size can be very important. When evaluating a strategy, its capacity is usually overlooked but its performance might be considerably affected by the invested capital. For instance, strategies involving small cap companies can appear very profitable, but their performance can deteriorate very fast for higher levels of assets under management (AUM). The main reason being that small cap companies are usually associated with more stringent liquidity constraints, which makes them more difficult to trade without moving their stock price.
In a previous study, we proved how earnings sentiment data can provide an edge over earnings consensus estimates. Nevertheless, a strategy built on top of a potentially sparse signal like earnings has some drawbacks including small portfolio sizes and limited capacity. However, since news like earnings guidance or other earnings related news can provide direct information about the future growth prospects of a company, we can also expect that it will impact those economically-linked companies that depend on it. This offers an opportunity to increase portfolio size by focusing on companies in its network.
In this paper, we investigate whether companies with earnings sentiment propagate its effect onto their suppliers, customers, or competitors, and thereby improves the ability of the signal to provide attractive performance when AUM increases. We show that the spillover strategies, combined with the original, allow to trade considerably larger portfolios. This translates into an overall strategy that is more diversified and less liquidity constrained, thus able to absorb higher levels of AUM and provide better performance in terms of Information Ratio as AUM scales.
To evaluate the scalability of our proposed signals, we develop a backtesting framework in order to assess the marginal trade-off between risk and return as more capital is allocated towards the strategy. Specifically, this is obtained by exploiting minute data on trading volume and price to impose a set of liquidity constraints, and hence adhere to the price-taker hypothesis, where the investor’s own trading has no impact on the market.
The paper is organized as follows: Section 2 describes the different data sources that we use; Section 3 follows with a brief introduction of our earnings sentiment indicator, as well as the methodology adopted for propagating the signal across the supply-chain and competitive landscape, and for evaluating strategy scalability. Results are provided in Section 4; and Section 5 presents our general conclusions.
Please use your business email. If you don't have one, please email us at email@example.com.
We will process your personal data with the purpose of managing your personal account on
RavenPack and offering our services. You can exercise your rights of access, rectification,
erasure, restriction of processing, data portability and objection by emailing us at firstname.lastname@example.org. For more information, you can
Your request has been recorded and a team member will be in touch soon.
High inflation has returned in developed markets after decades of lying low. In our latest paper, we show how to build an inflation-based asset allocation strategy using sentiment data and we illustrate that sentiment-based strategies outperform models that depend merely on past observed inflation values.
This year's RavenPack Research Symposium brought two intense days of knowledge sharing in London and New York, from 25 top experts in natural language processing, quantitative investing and machine learning. Together, we explored how firms can leverage new language models to generate alpha, better manage risk and respond to calls for more sustainable investment practices.
Human capital is at the heart of value creation. Our latest research demonstrates how unprecedented workforce insights, sourced from over 200 million job postings, can generate more alpha.