What is Quantamental Investing?

The term 'quantamental' is a portmanteau of quantitative and fundamental analysis that refers to combining both techniques for the purpose of investment management.

a month ago   •   7 min read

By Peter Foy

The term 'quantamental' is a portmanteau of quantitative and fundamental analysis that refers to combining both techniques for the purpose of investment management.

Quantamental investing has become an increasingly popular approach to investment management and seeks to increase risk-adjusted return by combining the scientific rigor of quantitative analysis with the more discretionary, fundamental analysis of assets.

By pairing human insights with the advances in data science and machine learning, quantamental investing will be a core aspect of the asset management industry going forward.

As stated in this Harvard Business Review article on machine learning:

The bottom line is that while ML can greatly improve the quality of data analysis, it cannot replace human judgment. To utilize these new tools effectively, asset management firms will need computers and humans to play complementary roles.

In this article, we'll discuss key concepts of quantamental investing and real-world applications in both equity and crypto investing, including:

  • Quantitive Finance Overview
  • Quantitative Finance Challenges
  • Fundamental Analysis Overview
  • Fundamental Analysis Challenges
  • Why Quantamental Investing is the Future
  • Applications of Quantamental Investing

Quantitive Finance Overview

First, let's briefly go over the unique challenges and opportunities of quantitive finance.

Quantitive finance is an expansive and complex field, although in general, it refers to the process of using large amounts of data to guide trading and investment strategies.

Quantitative strategies can either be completely autonomous trading as is the case with high-frequency trading, or it can simply assist in the investment decision process.

The type of data used by quants and data scientists also varies widely and ranges from typical stock market data such as OCHLV (open, close, high, low, volume). These days, however, many quantitive hedge funds also make use of alternative data such as:

  • Geolocation, or foot traffic
  • Satellite imagery
  • Credit card transactions
  • Social media data

This industry has grown tremendously in the past 5 years, and Deloitte estimates that asset managers are spending $2-3 billion per year on acquiring and processing alternative data.

Quantitative Finance Challenges

Despite this growth in quantitive investing, it isn't without its challenges. In particular, as discussed by the synthetic data company Blackarbs, a few of the most common challenges in quantitive finance include.

  • Data Scarcity: There is only one historical time series for each financial instrument, which means there can often be a lack of data diversity.
  • Data Costs: Depending on the size of your institution's resources, market data fees can limit the ability to research and develop profitable trading strategies.
  • Backtest Overfitting: One of the main challenges with backtesting quantitive trading strategies is overfitting.

Now that we have a brief overview of quantitive finance, let's briefly review the much more traditional approach: fundamental analysis.

Fundamental Analysis Overview

Whereas quantitative analysis involves using data science and machine learning to extract trading signals and investment insights, fundamental investing focuses on determining the true value of a company or asset.

In the context of equities, fundamental analysis involves determining the health of a company through metrics such as their balance sheet, cash flow, and income statements. This data is all used to forecast the company's growth prospects, risk factors, and relative value.

Aside from quantifiable metrics such as the company's financial statements, fundamental analysis will often involve a qualitative aspects such as the company's management team, upcoming news events, and the broader macroeconomic landscape.

By combining quantifiable data and non-quantifiable metrics, the goal of fundamental analyst is to understand the company's growth story alongside an estimation of its true value.

In doing so, analysts will often compare the current valuation of the stock relative to peers through ratios such as the price-to-earnings (P/E), price-to-book (P/B), and so on.

Fundamental Analysis Challenges

Fundamental analysis and stock pickers have been around for a long time, although it is also not without its challenges. Effectively analyzing a company's balance sheet and growth prospects can take years to master. Furthermore, since there is always a qualitative element to fundamental analysis, it is often thought of as more of an art than a science.

Another challenge for fundamental investors is how time-consuming it can be. For example, if you're analyzing every company in the S&P 500 and reading their quarterly and annual filings, this can take weeks or months to complete.

To solve these challenges, combining quantitative and fundamental analysis is an emerging trend amongst fund managers that will only continue to grow in the coming years.

Why Quantamental Investing is the Future

Quantamental investing provides asset managers with the advantages of data science and machine learning algorithms and complements it with their own knowledge and experience of markets.

Since quantitative models that trade completely autonomously can take years to develop and significant technical expertise, asset managers are increasingly looking use these techniques as a part of their investment approach instead of having it take over completely.

As we'll discuss below, quantitative models can significantly increase the speed of an investment manager's analysis, and also help them identify potentially undiscovered assets.

While the largest asset managers such as Blackrock and Man Group have been leading the way for years and using artificial intelligence and data science in their investment approach, many other investment professionals have started to incorporate it into their process.

As a report on AI in investment management by the CFA Institute writes:

Successful investment firms of the future will be those that strategically plan on incorporating AI and big data techniques into their investment processes. Successful investment professionals will be those who can understand and best exploit the opportunities brought about by these new technologies.

Now that we've discussed what quantamental investing is, let's look at several real world use cases of this quantitative approach for portfolio managers and investors.

Applications of Quantamental Investing

Below we'll look at three machine learning-based approaches to quantamental investing, including:

  • Sentiment analysis
  • Excess return estimates
  • Equity rankings

Sentiment Analysis

The first and most common technique used in quantamental investing is sentiment analysis. Sentiment analysis is performed using a machine learning technique called natural language processing (NLP).

Given the massive corpus of text data available on public companies including social, news, and SEC filings, this technique can be used to speed up and improve the investment research process.

Social Sentiment

Social sentiment allows investors to analyze thousands of tweets and online commentary about a stock in order to analyze the overall sentiment at a glance.

For example, in the MLQ app AI investment research platform, we provide investors with social sentiment that provides the following insights:

  • Overall Sentiment: Number between -1 and 1 where -1 is most bearish and 1 is most bullish.
  • Total Scores: Number of social data inputs to generate the sentiment value.
  • Positive Sentiment: Percent of social messages with positive sentiment.
  • Negative Sentiment: Percent of social messages with negative sentiment.
Demo Data

News Sentiment

Financial news is another example of text data that can be analyzed and summarized into a sentiment score. With the sheer amount of news on each company, this can save analysts a significant amount of time in their quantitative research.

In the MLQ app, for example, we provide stock sentiment from the last 7 and 30 days of public financial news for ~5,000 US stocks.

The news sentiment scoring technology is based on a combination of various natural language processing techniques. The sentiment score assigned to each stock is a value ranging from -1 (most negative) to +1 (most positive) and is updated daily.

Demo Data

SEC Filing Sentiment

Similarly, with each quarterly and annual SEC filings there is can be an overwhelming amount of text data for investors to analyze. By using natural language processing, analysts can go through hundreds of filings in a short period of time.

After reviewing each SEC filings sentiment, the analyst can then decide which ones they want to investigate and read more thoroughly.

The SEC Filing Sentiment section of the MLQ app provides the following data:

  • Language Metrics: This includes metrics about the language used in a companyโ€™s most recent annual or quarterly filings (10Ks and 10Qs). This includes metrics on the financial sentiment and the scores based on the prevalence of words in the statement categorized into four themes: constraining language, interesting language, litigious language, and language indicating uncertainty.
  • Similarity & Differences in Language Metrics: This compares sentiment and language metrics from the companyโ€™s most recent report (annual or quarterly) to the report from last year (10K) or the corresponding quarter the prior year (10Q).
Demo Data

ML-Based Stock Rankings

Finally, machine learning can be used to rank equities based on a number of market factors. In the MLQ app, the data provider takes in over 200 factors and signals including fundamentals, pricing, technical indicators, and alternative data, and then uses an ensemble machine learning technique to analyze and rank stocks.

Demo Data

Crypto On-Chain Analysis

In terms of cryptocurrencies, quantamental investing can be done with the help of data science and ML-based insights from on-chain analysis.

Powered by IntoTheBlock, the data is sourced from an AI company that leverages machine learning and advanced statistics to extract intelligent signals for crypto-assets.

The on-chain analysis trading signals include:

  • New Network Growth
  • Large Transactions
  • Concentration
  • In the Money

Summary: Quantamental Investing

In summary, when it comes to comparing quantitive vs. fundamental analysis, the best approach is to combine both techniques in a quantamental strategy.

Quantamental investing allows investors to take advantage of the advances of data science and machine learning, while still making use of their own discretion, knowledge, and expertise of markets.

Through the process of quantamental investing, investors and analysts are able to discover new opportunities and speed up their research process. Ultimately, a quantamental approach leads to an investment management process that is greater than the sum of its parts

Spread the word

Keep reading