AI Hedge Funds: The Use Of Alternative Data To Make Trading Decisions

The article was written by Aline Rzetelna, a Financial Analyst at I Know First.

“I believe this Artificial Intelligence is going to be our partner. If we misuse it, it will be a risk. If we use it right, it can be our partner.” – Masayoshi Son

AI Hedge Funds


      • Hedge Funds Are Increasingly Turning to Artificial Intelligence
      • Different Methods of Acquiring Alternative Data & Difficulties
      • How I Know First Uses Artificial Intelligence and Machine Learning for Stock Markets Forecasting Solutions

Hedge Funds Are Increasingly Turning to Artificial Intelligence

AI Hedge Funds: The emergence of Machine Learning and Deep Learning, subfields of Artificial Intelligence, have revolutionized the hedge fund industry. Artificial Intelligence is the capability of machines to imitate and replicate human intelligence. Machine Learning is the science of getting computers to act without being explicitly programmed. Deep Learning is a wing of Machine Learning, in which algorithms automatically learn from unstructured or unlabeled data and make predictions based on this data.

Hedge funds need to have large capital returns to justify their high fees. Therefore, Artificial Intelligence is being used in this industry in order to help hedge fund managers to perform accordingly. It helps in the process of making trading predictions, of finding investment opportunities and identifying patterns that offer an edge in investing.

Hedge funds are increasingly turning to AI. In accordance with 2017 Global Hedge Fund and Investor Survey provided by the accounting firm EY, nearly half of the managers are using nontraditional/ next generation data (see chart below). Moreover, a recent research from Deloitte showed that 70% of the new hedge funds launching in 2018 will include investment processes supported by AI and Machine Leaning.

Source: EY 

Different Methods of Acquiring Alternative Data & Difficulties

Artificial Intelligence is increasingly present in our daily life. Therefore, Hedge Funds couldn’t be out of this way. The problem that remains is how investors can find data. The new concept surging is ‘alternative data’, which consists of methods of acquiring information, such as: website scraping, credit card tracking, geolocation and satellite imagery. Yet there are still some issues regarding these techniques.

Website Scraping

In a world of the Internet of Things (IoT), in which physical devices embedded with electronics softwares are connected to the Internet, online tracking is getting more accurate everyday and harder to evade. Many of our online activities leave a digital fingerprint. Mobile phones can be tracked, phones can be scanned, online purchases monitored.

What is happening now is that the alternative data vendors are scrapping the big data left by digital fingerprints and are turning them into tradable signals. They sell this digital information to investment groups who are desperate for an edge in the market. According to BlackRock, the world’s largest asset manager: “In order to generate sustained returns, investors must embrace the task of acquiring, analyzing and understanding the ever-growing data universe. Those that fail to do so run the risk of falling behind in a rapidly changing investment landscape.”

Although the fact that data vendors are scraping this alternative data, this industry is still unregulated. Thus, some fear that this information will turn to be legally protected. The question that follows is to what extent the use of this digital fingerprint data can be considered as fair and at what point it can already be considered as a disrespect in privacy.

Credit Card Tracking

One of the most valuable information for hedge funds is in what consumers are spending their money on. Thus, credit card companies are sometimes considered as the main gold mine for data. Although it only offers a partial view of sales trends, this data combined with other data sets can offer vital insights of consumers patterns.


Geolocation can be utilized by hedge funds as a clue on consumer trends. The geolocation consists in the identification of the geographic location of an object, mobile phone or internet-connected computer terminal.

As an example of how useful this alternative data can be: on April 2016, CEO of Foursquare, Jeff Glueck, predicted that Chipotle’s Q1 sales would drop 30%, once it tracked the foot traffic pattern of consumers with the employ of geolocation intelligence.

Despite its accuracy, this method of acquiring information to make trading strategies can be consider as invasive in individuals, communities and entire nations lives.

Satellite Imagery

Satellites can be considered as eyes in the sky. They efficiently provide images that can help in the process of making investment decisions. For example: they can track the number of cars in parking lots, which can serve as a clue to know which stores are more popular or which companies may be having layoffs if less cars are showing up.

These images can also help to determine the health of the soil and agriculture on the ground, which is highly valuable for commodities investors. Moreover, satellites can access, on a real-time base, shipping movements, which can contribute to better understanding of costs and health of companies’ supply chain and to build an accurate knowledge of the trend of the markets.

In the past, investors analyzed financial reports and news for insights on the company performance. Alternative data has surged to facilitate the researching with the use of sophisticated technology. Therefore, investors are given the opportunity to make better-informed decisions in a more efficient way.

Growing Market of Alternative Data

Alternative data also comes with a challenge: the vast amount of digital information, which is generated everyday. As the demand for alternative data is increasing, the need for companies, which offers to scrape, clean and sell this data to the investment community is also growing. As you can see in the chart below, the number of alternative data providers is rapidly increasing over the past few years.

Source: Financial Times 

According to a report by consultancy Opimas, hedge funds’ spending on alternative data sources is growing by around a fifth each year and is expected to hit $7 billion by 2020.

How I Know First Uses Artificial Intelligence and Machine Learning for Stock Markets Forecasting Solutions

I Know First is a fintech company that provides state of the art self-learning AI based algorithmic forecasting solutions for the capital markets to uncover the best investment opportunities. I Know First’s AI-based algorithm, which incorporates multi-layered neural networks and genetic algorithms, allows us to model the market without human derived assumptions. By doing so, our algorithm is able to achieve flexibility with regards to the model and evolve with the ever-changing markets. The algorithm continually learns and adapts based off of its previous forecasts, and adapts to new conditions and features quickly.

Additionally, the design of the algorithm further enhances its capabilities to be able to make predictions in circumstances not observed before, as a result of its learning experience and intelligence. This is something one cannot achieve without AI technology. This maximizes efficiency of employees when applied to financial institutions. Financial employees become more efficient when they have help from the I Know First algorithmic system. The algorithm is already in use among institutional investors; the product is used by research and analyst teams in hedge funds, banks and family offices or by financial advisors.

I Know First develops, back-tests and offers systematic trading strategies which are used in partnerships with hedge funds and other asset managing entities. These strategies are rules-based and utilize algorithmic forecasting indicators in order to rank and select the trades as well as time the execution. Here the final product are the trades recommendations for execution, depending on the investment strategy profile chosen. The type of strategies varies, including mean-reversion logic and more trend focused approaches, all generating high positive alpha while keeping beta in the 0.3-0.8 range, yielding overall high risk-adjusted returns. The strategies can be used in partnership with I Know First to launch hedge funds, mutual funds or other investment vehicles.

Secondly, the two-fold business model puts I Know First in a unique position: offering custom and standardized algorithmic forecasts to variety of clients (institutional and retail) and researching and developing systematic trading strategies for fund management purposes on a revenue sharing basis. The business model proved itself and I Know First has earned clients’ trust for over four years now and is partnering with large financial institutions not only in Israel (asset manager) but also Europe (bank), United States (wealth management) and Japan (financial information provider).

For further information on this topic, please review related articles:


To subscribe today and receive exclusive AI-based algorithmic predictions, click here

Extreme Networks Analysis