latamen
Quant modeling can use non-numerical data, too

Quant modeling can use non-numerical data, too

10-12-2021 | Insight

We find that text analysis can predict the risk and return characteristics of corporate bonds.

  • Patrick  Houweling
    Patrick
    Houweling
    Co-Head of Quant Fixed Income and Lead Portfolio Manager
  • Robbert-Jan 't Hoen
    Robbert-Jan
    't Hoen
    Researcher

Speed read

  • More than 80% of all corporate information is in an unstructured form
  • Literature finds that text in SEC filings predicts return and volatility of stocks
  • We show that results from the literature carry over to corporate bonds

It is estimated that over 80% of all business-relevant information is in an unstructured form, such as text, video, or audio.1 However, financial models traditionally only use numerical data, such as market prices and company accounting data. Hence, tapping into the large pool of unstructured data has the potential of enriching existing models. We investigated the opportunities that unstructured data present for investing in corporate bonds.2

Stay informed on our latest insights with monthly mail updates
Stay informed on our latest insights with monthly mail updates
Subscribe

Mining abundant sources of non-numerical data

Textual data is an important source of non-numerical data. Examples include news articles, social media posts, transcripts of management presentations and corporate reports. Until recently, usage of such text sources in analysis required human intervention to code attributes into numerical form – a slow and tedious process. Nowadays, due to advances in natural language processing (NLP) and the immense growth in computing power, text mining techniques can be used to systematically analyze vast amounts of text data.

Academics as well as practitioners have started analyzing text data for the purpose of predicting the risks and returns of stocks and bonds. One strand of research investigates the information content of corporate reports filed by publicly listed companies in the US with the Securities and Exchange Commission (SEC). Of these SEC filings, most attention is directed towards the annual (Form 10-K) and quarterly (Form 10-Q) reports. The reports are very extensive, owing to laws and regulations that prohibit companies from making materially false or misleading statements, and from omitting material information that would render disclosures misleading. Along with the numerical data from the financial statements, these filings contain large volumes of unstructured textual information.

The information in 10-Ks and 10-Qs should enable any investor to fully understand the state of a company. In practice, however, valuable information in these reports is easily overlooked, because of the daunting challenge of reading and grasping many pages of formal and often very technical text.3 These reports therefore provide an attractive avenue of research for the application of computer-based text analysis.

Data collection and pre-processing

We obtain all 10-Ks and 10-Qs of publicly listed US issuers of corporate bonds in the Bloomberg US Corporate Investment Grade and High Yield ex. Financials indices. The sample covers the period from 1994 to 2017 and contains a total of 212,400 filings, of which 57,952 are 10-Ks and 154,448 10-Qs.

Figure 1 | Filing size

Source: Robeco, EDGAR. Sample period 1994-2017.

To facilitate later analyses, we first clean each document so that only the text, numbers and symbols in the main body of the original filing remain. Figure 1 shows the average size of the cleaned files over time, as measured by the total number of characters. As expected, we find that 10-Ks are, on average, significantly larger than 10-Qs. Moreover, there is a strong upward trend in the size of 10-Ks and 10-Qs. This is driven largely by the gradual increase over time in required disclosures.

Text analysis

The next step in the research is to process the cleaned text data so that it becomes understandable to a computer. A commonly used method to convert text into a numerical format is the Bag-of-Words (BoW) model. BoW is an NLP technique that reduces the complexity of text data by removing information about word order and context. All that remains of each filing is a list of term frequencies, i.e., the number of times each unique word appears. The idea behind the model is that the more frequently a term is used, the more important it is.4

Changers and non-changers

A recently published academic article documents that the similarity of a company’s consecutive 10-Ks and 10-Qs is a significant predictor of stock return and stock return volatility: companies that make more changes to the text of their report compared to their previous report (which the article labels as ‘changers’) underperform companies with fewer changes (labeled as ‘non-changers’) by a wide margin.5 The rationale for this finding is that firms tend to repeat what they reported previously and that they are only required to change the text if there are material changes to the company or to its circumstances over the reporting period. Changes in the text are thus interpreted as being negative. Although extensive text changes are not necessarily a bad sign, analysis does show that these are mostly related to negative events and negative future stock returns.

In our research, we test if a similar effect exists for corporate bonds. If the degree of similarity between consecutive 10-Ks and 10-Qs is truly linked to firm performance, then we expect to see this reflected in corporate bond returns as well. To gauge the similarity between reports, we compare the text in a report with that of the same report published a year previously, i.e., a 10-K is compared with previous year’s 10-K, and a 10-Q with a 10-Q of the same quarter in the previous year.

We evaluate the performance of changers versus non-changers on our sample of US investment grade and high yield issuers over the 1997-2017 period. Our hypothetical investment strategy for this research goes long in the bonds of the companies whose reports showed the fewest changes, and goes short in the bonds of the firms with the most changes.

We find that, in investment grade as well as in high yield, non-changers have outperformed changers by over 50bps per year and have been less risky than changers, resulting in higher Sharpe ratios for non-changers. Overall, we find that the degree of similarity between consecutive reports has predictive power for corporate bond risk and return, with stronger statistical significance in investment grade than in high yield.

1 http://breakthroughanalysis.com/2008/08/01/unstructured-data-and-the-80-percent-rule/
2 This insight is based on an extract from the paper “Continuous innovation in factor credit strategies”, April 2021, by Patrick Houweling, Frederik Muskens and Robbert-Jan ‘t Hoen.
3 Loughran & McDonald, 2014, “Measuring readability in financial disclosures”, The Journal of Finance, 69(4), 1643-1671.
4 We filter out uninformative words using the popular stop word list of Loughran and McDonald: https://sraf.nd.edu/textual-analysis/resources/#StopWords
5 Cohen, Malloy & Nguyen, 2020, “Lazy prices”, The Journal of Finance, 75(3), 1371-1415.

Logo

Important information

The Robeco Capital Growth Funds have not been registered under the United States Investment Company Act of 1940, as amended, nor or the United States Securities Act of 1933, as amended. None of the shares may be offered or sold, directly or indirectly in the United States or to any U.S. Person (within the meaning of Regulation S promulgated under the Securities Act of 1933, as amended (the “Securities Act”)). Furthermore, Robeco Institutional Asset Management B.V. (Robeco) does not provide investment advisory services, or hold itself out as providing investment advisory services, in the United States or to any U.S. Person (within the meaning of Regulation S promulgated under the Securities Act).

This website is intended for use only by non-U.S. Persons outside of the United States (within the meaning of Regulation S promulgated under the Securities Act who are professional investors, or professional fiduciaries representing such non-U.S. Person investors. By clicking “I Agree” on our website disclaimer and accessing the information on this website, including any subdomain thereof, you are certifying and agreeing to the following: (i) you have read, understood and agree to this disclaimer, (ii) you have informed yourself of any applicable legal restrictions and represent that by accessing the information contained on this website, you are not in violation of, and will not be causing Robeco or any of its affiliated entities or issuers to violate, any applicable laws and, as a result, you are legally authorized to access such information on behalf of yourself and any underlying investment advisory client, (iii) you understand and acknowledge that certain information presented herein relates to securities that have not been registered under the Securities Act, and may be offered or sold only outside the United States and only to, or for the account or benefit of, non-U.S. Persons (within the meaning of Regulation S under the Securities Act), (iv) you are, or are a discretionary investment adviser representing, a non-U.S. Person (within the meaning of Regulation S under the Securities Act) located outside of the United States and (v) you are, or are a discretionary investment adviser representing, a professional non-retail investor. Access to this website has been limited so that it shall not constitute directed selling efforts (as defined in Regulation S under the Securities Act) in the United States and so that it shall not be deemed to constitute Robeco holding itself out generally to the public in the U.S. as an investment adviser. Nothing contained herein constitutes an offer to sell securities or solicitation of an offer to purchase any securities in any jurisdiction. We reserve the right to deny access to any visitor, including, but not limited to, those visitors with IP addresses residing in the United States.

This website has been carefully prepared by Robeco. The information contained in this publication is based upon sources of information believed to be reliable. Robeco is not answerable for the accuracy or completeness of the facts, opinions, expectations and results referred to therein. Whilst every care has been taken in the preparation of this website, we do not accept any responsibility for damage of any kind resulting from incorrect or incomplete information. This website is subject to change without notice. The value of the investments may fluctuate. Past performance is no guarantee of future results. If the currency in which the past performance is displayed differs from the currency of the country in which you reside, then you should be aware that due to exchange rate fluctuations the performance shown may increase or decrease if converted into your local currency. For investment professional use only. Not for use by the general public.

I Disagree