Why AI can help you beat the market

Humans have always welcomed other beings in finance: over twenty years ago, some of the best Wall Street traders were outsmarted by Raven, a chimpanzee who picked stocks by throwing darts.

Her index, called MonkeyDex, became one of the biggest sensations at the turn of the century after delivering a 213% gain.

Perhaps because animals are not so easy to fit in offices, people have turned to other kinds of brains to choose equities.

Big institutions are resorting to artificial intelligence (AI) to analyse stocks collating all sorts of information coming from a plethora of sources.

In fact, while investments could previously be assessed based on financial reports and share price movement – what is called structured data – markets have been heavily influenced by unstructured data over the past few years.

These can be anything from earning calls transcripts, major political events but also social media chatter: in 2021, it appears that a tweet by Elon Musk can potentially make or break a stock.

The AI process is entirely rational as it doesn’t rely on emotional reactions or the investment manager’s gut feeling, while its machine learning skills apply previous experience to new data to continuously improve performance.

Who’s doing it

Some of the big players have already established in-house AI research centres, such as Goldman Sachs and BlackRock.

In 2019, Goldman Sachs led a US$72.5mln investment round in H20.ai, a software that helps companies automate their internal processes using AI.

The investment bank said the results with their investee were “promising” and it was planning to look into the use of AI models across the equity trading floor.

Meanwhile, BlackRock is investigating how to use AI to crack the usually opaque world of private equity to assess risk.

Last year, HSBC PLC (LON:HSBA) launched the AI Powered US Equity Index (AiPEX) family using technology developed by EquBot and IBM Watson.

AiPEX learns from data points such as a company announcement, a tweet, a satellite image of a store parking lot, or even the tone of language a chief executive uses during an earnings presentation.

The information is used to evaluate the 1,000 largest US public companies and select those whose stock prices are poised for growth, with a portfolio rebalancing occurring monthly.

EquBot, one of the project developers, was also the first one to launch ETFs entirely powered by AI in the US.

AIIQ and AIEQ gather information from quarterly releases, news articles, market activity and social media to select stocks with potential to appreciate, all as they keep learning from previous experience.

Unlike other AI-powered funds, which may require big investments to get access to, they can be bought for as little as the price of one share because of their ETF nature.

“We like to start with the analogy that it basically replicates thousands of research analysts and traders working around the clock to help us learn what to invest in and when,” Equbot chief investment officer and co-founder Chris Natividad told Proactive.

“The reality is, it’s more than that because all these thousands of traders and research analysts speak a dozen different languages and oh, by the way, they know what each other knows all at the same point in time, because these models dynamically move and adjust as new market data is piped in.”

But not all AI is created equal, Natividad noted, so investors can rely on different degrees of technology based on their needs.

It’s only the beginning

Equbot reckons that by 2040, 99% of investment management groups will be using AI in some form and others seem to agree.

In a survey on 100 US wealth managers published last December by Accenture, most respondents recognised the benefits of adopting AI, but said they were struggling to scale it across their firms.

They said…