subscribe: Daily Newsletter

 

Machine learning powers unit trust fund

0 comments

NMRQL Research, the fintech player co-founded by former First National Bank CEO Michael Jordaan, launched a unit trust fund powered by machine learning — believed to be a first in South Africa.
The NMRQL SCI Balanced Fund, administered by the Sanlam Collective Investments platform, is a FSB-approved collective investment scheme compliant with Regulation 28, and aims to achieve steady long-term growth of capital and income. This will be achieved by investing in a diversified portfolio of domestic and international assets, where the asset allocation and stock selection is systematically managed using machine learning algorithms.
The machine learning-powered computational investment process is believed to allow NMRQL to discover hidden patterns in underlying big data. Once discovered, these patterns can be exploited to forecast returns across all asset classes and markets, resulting in steady long-term growth of capital and income.
The fund may comprise a combination of assets in liquid form, money market and interest-bearing instruments, bonds, corporate debt, equity securities, property securities, preference shares and convertible equities. Its benchmark is the Multi Asset High Equity category as recorded by the Association for Savings and Investment South Africa (ASISA).
The annual investment fee of 0,9% is inclusive of a management and admin fee, with a 10% performance fee applied should the fund outperform the average performance of all funds within the Multi Asset High Equity ASISA category.
According to NMRQL co-founder and CEO Tom Schlebusch, the new investment philosophy changes the current biased, human-centric investment management process to a non-emotive, unbiased algorithmic-driven process that continuously learns and adapts to changing environments.
“Machine learning equips fund managers with the tools to assess historical and present data, to help predict future risks and returns based on large volumes of data,” he says. “At NMRQL we process around 2-million data points each time we rebalance our portfolio. This could include quantitative, fundamental, economic or technical variables in order to discover and exploit repeatable patterns, helping us achieve our goal of delivering superior returns for clients.”
Jordaan says that machine learning has already disrupted the fund management industry globally. “The launch of this fund in South Africa marks the start of a paradigm shift that the local investment management industry will soon experience.
“In addition to the vast amount of data that the algorithm is able to process, the investment philosophy eliminates emotive decision making, which allows the model to remain rational at all times.
“As humans we suffer from various cognitive biases. These biases negatively impact our objectivity and reasoning skills daily, and are compounded when financial repercussions are involved,” Jordaan says.
Stuart Reid, chief engineer at NMRQL, says that the NMRQL algorithm is testable, and uses a walk-forward approach that allows fund managers to use historical data to investigate exactly how the fund would have behaved using only information available at that point in time. By using more than 1 000 different models and applying an algorithmic voting system, NMRQL is then able to produce portfolios with the best possible chance of outperformance.
The fund is currently available on the Glacier and Momentum platforms.