Blending tech into investment

1234

On the wealth management side, Farringdon Asset Management’s robo-advisor Algebra now uses a machine-learning strategy in its sharia-compliant investment strategy. It’s implemented using the neural network technology provided by Maxsys AI, a US company specialising in AI for investment management.

Neural networks attempt to replicate with software the learning and information storage patterns of a human brain. They learn from data feeds, and are expected to become “smarter” over time.

The data used by Algebra’s AI consist of traditional financial data, as well as unstructured “big data” gathered from the internet.

“We are training it by bringing non-traditional financial data, primarily the social media news flow,” Martin Young, the firm’s CEO, told FSA.

The AI strategy works with the universe of 125 US companies from the S&P 500 index that have been certified as sharia-compliant.

The AI system processes US social media data and news feeds, scouring them for relevance to these companies. It was “trained” on historical data to learn the patterns corresponding to positive and negative movements in the stock prices.

Farringdon has said in a statement that the AI-powered portfolio is not a high-frequency trading strategy but a long-term investment approach. A person will oversee any investment decisions made by the algorithm.

‘Ridiculously high’ returns?

In back-testing, Farringdon’s AI-powered strategy delivered “ridiculously high” returns, according to Young, roughly double those of Algebra’s smart-beta portfolio, the other option available to the robo-advisor’s clients.

However, Young admitted that back-testing tends to have positive bias.

Young also admitted that the ultimate proof of the algorithm’s skill will be in a market correction or during a period of high volatility.

“The last time everyone got excited about algorithmic trading, they found out that algorithms were the biggest gamblers in the market,” he said. “It could as well be the same case with this.”

1234