Quantpedia is The Encyclopedia of Quantitative Trading Strategies
We've already analyzed tens of thousands of financial research papers and identified more than 1000 attractive trading systems together with thundreds of related academic papers.
- Unlock Screener & 300+ Advanced Charts
- Browse 1000+ uncommon trading strategy ideas
- Get new strategies on bi-weekly basis
- Explore 2000+ academic research papers
- View 800+ out-of-sample backtests
- Design multi-factor multi-asset portfolios
Natural language processing, or NLP for short, is the ability of a program to understand human language. Studies suggest there is a connection between investor's vocabulary and the profitability of their strategies.This research analyzes lexical metrics in 10-K & 10-Q reports. All publicly traded companies have to file 10-K & 10-Q reports periodically. These reports consist of relevant information about financial performance. Nowadays, there is a gradual shift from numerical to text-based information, making the reports harder to analyze. Still, the 10-K & 10-Q reports rightfully receive great interest from academics, investors and analysts.
BRAIN is one of the companies that analyze the 10-K & 10-Q reports using NLP. The main objective of The Brain Language Metrics on Company Filings (BLMCF) dataset is to monitor numerous language metrics on 10-Ks and 10-Qs company reports for approximately 6000+ US stocks. This paper focuses on the Lexical metrics of the BLMCF dataset, specifically lexical richness, lexical density, and specific density.
Fundamental reason
The combination of the high and increasing volume of published 10-K & 10-Q reports and their gradual shift to nonnumerical information leads to the premise that fundamental analysts cannot identify crucial information in the “white noise” about the actual and future performance of the company. The companies like BRAIN, which analyze the 10-K& 10-Q reports using NLP and give scores according to numerous language metrics, bridge the gap between the nonnumerical and numerical data. The research suggests that the richer the vocabulary of an investor is, the higher the lexical score the company gets and the better it performs.
Get Premium Strategy Ideas & Pro Reporting
- Unlock Screener & 300+ Advanced Charts
- Browse 1000+ unique strategies
- Get new strategies on bi-weekly basis
- Explore 2000+ academic research papers
- View 800+ out-of-sample backtests
- Design multi-factor multi-asset portfolios
Market Factors
Confidence in Anomaly's Validity
Period of Rebalancing
Number of Traded Instruments
Notes to Number of Traded Instruments
Complexity Evaluation
Financial instruments
Backtest period from source paper
Indicative Performance
Notes to Indicative Performance
Estimated Volatility
Notes to Estimated Volatility
Notes to Maximum drawdown
Sharpe Ratio
Regions
Simple trading strategy
The investment universe consists of top 500 US stocks by dollar volume. The stocks are sorted based on their lexical density and specific density score from the BLMCF dataset. Lexical density measures the structure and complexity of human communication in a text. A high lexical density indicates a large amount of information-carrying words. Specific density measures how dense the report’s language is from a financial point of view. In other words, how many finance- related words are used in the text. The investor goes long the top decile and short the bottom decile. Additionally, the portfolio is rebalanced on a monthly basis.
Hedge for stocks during bear markets
Yes – Based on the backtest in Quantconnect, the strategy has a negative beta of -0.029. The visual inspection of the equity curve also suggests that the strategy performs well during bear markets.
Out-of-sample strategy's implementation/validation in QuantConnect's framework(chart, statistics & code)
Related video
Related picture
Source paper
Hanicova, Kalus, Vojtko: <span style="font-size: 16px;">How to Use Lexical Density of Company Filings
Abstract: </span><span style="font-size: 16px;">This paper analyzes the application of natural language processing (NLP) on the 10-K and the 10-Q company reports. Using the Brain Language Metrics on Company Filings (BLMCF) dataset, which monitors numerous language metrics on 10-Ks and 10-Qs company reports, we analyze various lexical metrics such as lexical richness, lexical density, and specific density.</span><span style="font-size: 16px;">In simple words, lexical richness says how many unique words are used by the author. The idea is that the more varied vocabulary the author has, the more complex the text is. Secondly, lexical density measures the structure and complexity of human communication in a text. A high lexical density indicates a large amount of information-carrying words. And lastly, specific density measures how dense the report's language is from a financial point of view. In other words, how many finance- related words are used in the text.</span><span style="font-size: 16px;">Overall, we can say that this type of alternative data exhibits interesting results. Even though lexical richness produced the weakest results (of our strategies) when applied to the investment universe consisting of 500 stocks, it significantly improved when we expanded the investment universe to 3000 stocks. Moreover, the strategies based on the lexical density and specific density improved the Sharpe ratio even further.</span><span style="font-size: 16px;">In the Last section, we combine the two metrics (Lexical density and Specific density) in one strategy. Applying both of these metrics to the investment universe with 500 stocks produces a Sharpe ratio of 0.688.</span>
Other papers
Han, Henry and Wu, Yi and Zhao, Qianyu and Ren, Jie: Forecasting Stock Excess Returns With SEC 8-K Filings
Abstract: The stock excess return forecast with SEC 8-K filings via machine learning presents a challenge in business and AI. In this study, we model it as an im-balanced learning problem and propose an SVM forecast with tuned Gaussian kernels that demonstrate better performance in comparison with peers. It shows that the TF-IDF vectorization has advantages over the BERT vectorization in the forecast. Unlike general assumptions, we find that dimension reduction generally lowers forecasting effectiveness compared to using the original data. Moreover, inappropriate dimension reduction may increase the overfitting risk in the forecast or cause the machine learning model to lose its learning capabilities. We find that resampling techniques cannot enhance forecasting effectiveness. In addition, we propose a novel dimension reduction stacking method to retrieve both global and local data characteristics for vectorized data that outperforms other peer methods in forecasting and decreases learning complexities. The algorithms and techniques proposed in this work can help stakeholders optimize their investment decisions by exploiting the 8-K filings besides shedding light on AI innovations in accounting and finance.