Natural Language Processing

AgPa #72: Machine-Reading of Private Equity Prospectuses

Limited Partners versus Unlimited Machines: Artificial Intelligence and the Performance of Private Equity Funds (2023)
Reiner Braun, Borja Fernández Tamayo, Florencio López-de-Silanes, Ludovic Phalippou, Natalia Sigrist
CEFS Research Paper, URL/SSRN

This week’s AGNOSTIC Paper is somewhat outside my major area of competence, but I think it is a good example where we are heading to in the investment industry. Over the last years, it became quite standard that investors use the latest tools of machine learning to analyze non-quantitative information like text or images at a scale that hasn’t been possible before. So far, however, the efforts were mostly focused on public markets. In their not yet published working paper, this week’s authors show that there seems to be also a lot of potential for such methods in private markets.

  • Portfolio Company, Management Team, Investment Opportunity – The most common words of PE-managers
  • The complexity of PE-fund documents is related to fundraising success and performance
  • Machine learning and text data helps to select PE-funds
  • The machines seem to pick up meaningful concepts

Read the Full Post

AgPa #49: Machine Learning in Quant Asset Management

How Can Machine Learning Advance Quantitative Asset Management? (2023)
David Blitz, Tobias Hoogteijling, Harald Lohre, Philip Messow
The Journal of Portfolio Management Quantitative Tools 2023, URL/SSRN

This week’s AGNOSTIC Paper is a broad overview about machine learning in investment management. The authors outline the benefits and pitfalls of machine learning compared to “traditional” econometrics and present several use cases in the world of (quantitative) asset management. They also provide ideas for research governance to keep those powerful methods under control.

  • Benefits and pitfalls of machine learning in finance
  • Use cases of machine learning in asset management
  • Keeping it under control: research governance and protocol

Read the Full Post

Report Analytics USA #2

This post contains a lot of unsexy calculations and is fairly technical. But (in my opinion) there are some very interesting results. Not just for my particular strategy but for everyone who is active on Wikifolio.

First. Overall and especially after costs, my two Wikifolios weren’t a good alternative to a standard ETF on the S&P 500 index (from inception to March 11, 2022). To my defense, however, I stressed several times that the two Wikifolios are just a real-world test of my master thesis and I never marketed them as investments.

Second. I still believe that Wikifolio is a great platform to test strategies like mine, but it is not perfect. There are annoying technical issues, pretty high fees, and significant indirect trading costs. Depending on the liquidity of the stock, bid-ask-spreads and/or unfavorable FX rates amount to 40-80 basis points per transaction on average.

Read the Full Post

Report Analytics USA #1

This is the start of an ongoing series intended to share updates, insights, and backgrounds on the Report Analytics USA portfolios. To start with, I present the methodology that I currently use to implement the live portfolios on Wikifolio.

Heart of the process is a stock selection based on copy-paste of the most recently published annual and quarterly reports. I further divide this selection by market capitalization to create a “Large” and “Small” version of the Report Analytics USA portfolios.

All of this is just a starting point and I conclude this post with a roadmap of ideas to improve the strategy.

Read the Full Post

#2: Copy-Paste Outperformance

Every year, US companies must publish three quarterly and one annual report. Preparing those reports, however, is a lot of effort, does not improve operations, and reveals information to competitors.

How to deal with this? Correct, spend the time to create one comprehensive template and reuse it as long as possible. In an excellent research paper titled “Lazy Prices” (2020), the authors show that US companies are no exception from this: many annual and quarterly reports are basically just updated copies from the previous year.

What does this mean for investors? Since most of the report is just copy-paste, they should rather focus on differences between the current and previous report (for example, new paragraphs). It turns out that such changes are indeed very important: quantitative measures for report copy-paste predict future stock returns and help to achieve outperformance vs. common US indices.


Read the Full Post