The following was prepared by a third party unaffiliated with Millburn. Please see the important disclosures appearing here and below. PAST PERFORMANCE IS NOT NECESSARILY INDICATIVE OF FUTURE RESULTS. THE POTENTIAL FOR PROFIT IS ACCOMPANIED BY THE RISK OF LOSS.
The views and opinions expressed herein are those of the author and do not necessarily reflect the views of Millburn Ridgefield Corporation, its affiliates or its employees.
This document has been provided to you solely for information purposes and does not constitute an offer or solicitation of an offer or any advice or recommendation to purchase any securities or other financial instruments and may not be construed as such. There can be no assurance that an investment strategy will be successful. Historic market trends are not reliable indicators of actual future market behavior or future performance of any particular investment which may differ materially and should not be relied upon as such.
Without changing the substance of the article, certain elements have been redacted to comply with regulatory restrictions.
As China was welcoming in the world’s largest hedge funds four years ago, a Hangzhou-based quantitative fund was burning through motherboards and buying the wrong types of servers as it figured out machine learning.
Those “silly mistakes” quickly made way for Zhejiang High-Flyer Asset Management’s integration of machine learning into the strategies it uses to invest its 20 billion yuan ($2.8 billion) in assets, said Chief Executive Simon Lu. It now boasts its own super computer, a 60-strong team of engineers and data scientists and a confidence that belies its five years in the business.
Of the foreign competition that would once have been hard to fend off, it’s now a question of “who’s the best shooter when everyone has the same caliber gun,” Lu said. “The ability to understand the local market cannot be replicated or acquired that fast.”
High-Flyer is among Chinese quant funds closing the technological gap with veterans like D.E. Shaw & Co. and Two Sigma Investments LP as the U.S. firms make inroads on their home turf. Ranked as 2019’s No. 1 stock hedge fund by data provider Shanghai Suntime Information Technology Co., High-Flyer drew more assets last year than the combined collections of the dozens of foreign funds jostling for a piece of the market.
It isn’t alone. Second-ranked Shanghai Minghong Investment Management Co. has more than quadrupled the money it manages since 2018 to nearly 40 billion yuan, making it China’s biggest quant hedge fund. Inno Asset Management, ranked No. 3 by Suntime and founded by Xu Shunan, tripled assets since 2018. Quant hedge funds’ assets globally fell 12% this year through April 20, according to Eurekahedge Pte.
China’s quants are benefiting from being “latecomers,” borrowing technologies and algorithm models from abroad, according to UBS Asset Management Hedge Fund Solutions. While they may lack years of trading experience and often have less robust research and investment systems, they compensate with on-the-ground knowledge that foreign peers need time to gain, said Xia Kun, who’s responsible for fund of hedge fund management for UBS’s China private fund management business.
Competition is set to be intense in what Xia says is a “perfect market” for systematic trading. “The China market is huge and deep,” he said. “It’s very liquid, but at the same time still quite inefficient.”
Minghong and High-Flyer have distinguished themselves from the close to 9,000 hedge funds vying for investor attention in China. Those ranks have been swelled since 2016 by global stalwarts including Millburn Ridgefield Corp., Winton Group Ltd. and Man Group Plc, all craving a share of the 2.6 trillion yuan private securities funds market as clients in developed countries shift toward low-fee investments.
Even in this crowded field, quant trading is at a nascent stage, said Qiu Huiming, who worked for Millennium Management LLC and HAP Capital Advisors LLC in the U.S. before returning to start Minghong in 2014. Funds like his manage only 250 billion yuan, he estimates, while the market can absorb more than a trillion yuan in high-frequency plays and five times that in strategies that rely on fundamentals and hold long-term positions.
One early mover was High-Flyer, set up in 2015 by three engineers from Zhejiang University who began trading as students during the global financial crisis. The advantages of machine learning quickly caught the attention of co-founder Xu Jin, who was a visual navigation expert with China’s Jade Rabbit lunar rover program during his doctoral studies. The firm experimented with a multi-factor, price-volume based model in 2016, began testing it in trading the following year, then more broadly adopted machine learning-based strategies.
Returns have climbed 20% as a result, Lu said. Most of the group’s assets are split between the China Equity Fund CSI 500 Series, which was up 60% last year, and the China Absolute Return Series, which has generated an average 17% since inception more than three years ago. A focused machine learning strategy, with less than 100 million yuan, surged 99% in 2019 and is up 23% this year.
Minghong says it doubled assets in 2018 alone after moving to a medium-to-high frequency statistical arbitrage strategy that boosted excess returns by as much as 20 percentage points annually. It didn’t disclose absolute return figures. Rival Inno saw its best fund return 128% last year.
By comparison, BlackRock Inc.’s first China quant strategy gained 37.8% in 2019 and 12.2% as of April 30 since inception in May 2018, according to people familiar with the matter. BlackRock declined to comment. Quant funds globally averaged a return of 6.6% last year and lost 2.9% in the first quarter, Eurkahedge data show.
“Just because some foreign players’ products have lower returns doesn’t mean our research is superior,” said Minghong’s Qiu, noting that returns are not exactly comparable across different trading strategies. “But from the clients’ perspective, the advantages of our products are real.”
And in China, stunning returns draw funds more so than elsewhere.
The 26 foreign asset managers in China have cornered about 0.3% of the market, or 9 billion yuan, Shenzhen PaiPaiWang Investment & Management Co. data show. Two Sigma manages less than 100 million yuan, while BlackRock has less than 1 billion yuan. D.E. Shaw manages about 1 billion yuan. Two Sigma and D.E. Shaw also declined to comment.
Overseas firms need time to adapt, said Yan Hong, director of the China Hedge Fund Research Center at the Shanghai Advanced Institute of Finance. A short track record locally, restrictions on using their own offshore money to seed onshore products, and the time needed to build a local team is limiting them, he said. “It’s unrealistic to expect the foreign players to emerge quickly and overtake top local players in the near term.”
The dominance of retail investors and daily trading limits are among factors that make it hard for offshore strategies, said High-Flyer’s Lu. The real competition, he said, is keeping returns stable as a growing asset base strains the trading capacity of strategies.
Fund managers agree that local talent is paramount but challenging to attract. For the past 24 months, High-Flyer has been trying to recruit deep-learning scientists by offering salaries of as much as 2 million yuan. That sort of pay would rank among the top 20% best offers in the market, according to Beijing HeraldPartners Consulting Co. But filling the positions has been slow given the competition from tech giants like Tencent Holdings Ltd. and Alibaba Group Holding Ltd.
The answer for some international funds is joint ventures rather than the usual track of setting up as a wholly foreign owned private fund managers.
New York-based Millburn Ridgefield’s Chinese partner has been critical in building a local team, according to co-CEO Barry Goodman. Shanghai-based Quadrant Asset Management helped it find high-quality vendors to source “good, clean data” and understand the intricacies of execution, Goodman said. Although the nearly 50-year-old hedge fund has been using machine learning since 2013, “we felt like it was really important to approach the China market with a great deal of humility,” he said.
***
IMPORTANT DISCLOSURE AND RISK INFORMATION
This article was prepared by an independent third party, based in part on information provided by Milburn Ridgefield Corporation and its affiliated entities. No compensation was paid to the author or publisher of the article or any other person in exchange for publication of the article; however, Millburn has paid for the rights to reprint the published article. Millburn Ridgefield Corporation is the successor to an asset management organization that first began its operations in 1971. The term Millburn is used herein to refer to the activities of Millburn Ridgefield Corporation, its predecessors and its affiliated entities, except as indicated otherwise by the context.
This article reprint is not an invitation to invest in any investment strategy managed by Millburn but rather describes its approach to investing generally. The purpose of distributing this article is to provide further insight into Millburn s investment approach. This article is based on information available as of the date indicated. Any markets, models, leverage, portfolio weights and other data described herein change over time, but are accurate as of the date indicated herein. This presentation is not an invitation to invest in any investment strategy managed by Millburn and must be supplemented by certain disclosure when considering an investment, including important information concerning risk factors, conflicts of interest and other material aspects of an investment, which must be read carefully before any decision whether to invest is made. Investors may lose all or a substantial amount of their investments.
The information contained herein is only current as of the date indicated, and may be superseded by subsequent market events or for other reasons. Neither Millburn nor the author guarantees the accuracy, adequacy or completeness of such information. Neither Millburn nor the author assumes any duty to, nor undertakes to update forward looking statements. Nothing contained herein constitutes investment, legal, tax or other advice nor is it to be relied on in making an investment or other decision
PAST PERFORMANCE IS NOT NECESSARILY INDICATIVE OF FUTURE PERFORMANCE. THE POTENTIAL FOR PROFIT IS ACCOMPANIED BY THE RISK OF LOSS.
Commodity interest accounts are illiquid, speculative, employ significant leverage, and involve a high degree of risk. Commodity interest accounts involve high fees. There can be no assurance that an investment strategy will achieve its objectives.
NOTES TO PERFORMANCE
Estimated performance results are subject to final verification. Because it is difficult to attribute each actual position held by an account to a particular sub-strategy employed by that account, performance attribution by sub-strategy and net risk exposure are estimated based on internal calculations employing the sub-strategy and market weights utilized by the strategy. Accordingly, estimates may not precisely represent the positions held or results achieved by the strategy in actual trading.
Millburn Commodity Program (“MILCOM”) returns are net of all fees, expenses and transaction costs (2% per annum management fee; actual transaction costs; 0.25% per annum ordinary operating and administrative expenses; 20% annual profit share, subject to a high water mark), and reflect the reinvestment of profits.