From 30,000 stocks to 292 holdings: How Best Styles finds needles in a haystack

Start with a simple question: how many ways can you choose 300 stocks from a universe of 30,000?

The maths is not encouraging. The number of possible portfolios is so large it cannot be meaningfully expressed in everyday terms. It exceeds the estimated number of atoms in the observable universe.

No human team, however experienced, can evaluate that problem by instinct. No spreadsheet can solve it. And crucially, the challenge is not just picking the best 300 stocks. It is picking 300 stocks that are diversified across investment styles, free from unintended macro bets (rates, oil, FX, sector/country tilts), and positioned to harvest risk premia consistently across different market environments.

That is the problem Allianz Global Investors' Systematic Equity team has been working on since 1999. Their answer is a process that moves from a scored universe of over 30,000 companies down to a much smaller final portfolio: the Allianz Best Styles Global AC Equity fund has 292 holdings today (31/01/2026). Understanding how they do it explains a great deal about why the result performs the way it does.

Step 1: Scoring the universe (not just a benchmark list)

The process starts with breadth. The team's database spans more than 30,000 stocks listed in 47 countries, with prices updating around the clock. Every stock in that universe is scored across five styles: value, momentum, revisions, growth and quality. Those scores are generated using more than 500 return-predicting signals, drawing on over 8 trillion bytes of numerical data, 120 billion bytes of news and 21 billion bytes of earnings call transcripts.

Artificial intelligence (AI) plays a significant role here. A random forest model with 90 million nodes enhances the value score by identifying non-linear relationships between valuation metrics that a standard linear model would miss. A neural network trained on more than 100 years of market data produces an advanced trend signal. A natural language processing model trained on more than 200,000 company filings reads earnings calls and annual reports helps to avoid low-quality stocks.

Each of these tools is proprietary and customised. That matters because commercial AI tools carry biases specific to the data they were trained on, which can systematically favour certain sectors and produce contaminated investment signals if left uncorrected.

Once every stock has been scored, the team has a ranked list of the most attractive opportunities across the investment universe. That ranked list is the input to the next stage.

Step 2: Building a true multi-style blend

A ranked list can still produce a portfolio dominated by whichever factor is in fashion.

Portfolio construction therefore balances exposures, so each style (value, momentum, revisions, growth and quality) contributes meaningfully to the overall position. The low correlations between these styles are a benefit: when one style underperforms, others tend to hold up. Preserving that balance through portfolio construction is what converts the theoretical diversification benefit into a practical one.

Step 3: Removing the noise

The next stage is where the Best Styles approach differs most clearly from simpler factor strategies. Even a well-diversified multi-style portfolio can carry significant unintended exposures to macro risk factors. Sensitivity to interest rates, oil price movements, currency swings, sector dynamics and country-level economic conditions all contribute tracking error to a portfolio without delivering a compensating risk premium over time. They are, in the team's terminology, “unrewarding risk factors”.

Best Styles actively identifies and neutralises these through a barbell structure that creates an overweight of the extremes. For example, to mitigate oil price movements, the strategy might simultaneously overweight stocks that benefit most from a rise in oil prices and stocks that benefit most from a fall, while underweighting those in the middle. The net exposure to oil price risk across the portfolio is approximately zero.

The result is a portfolio whose returns are driven by the style premia it is deliberately targeting, not by accidental bets on economic conditions the team has not consciously taken.

What the process produces

In the case of the Allianz Best Styles Global AC Equity, the output of this process is a portfolio of 292 holdings with a 63% active share and a three-year information ratio of 1.53 (a measure of risk-adjusted outperformance that reflects the consistency of the approach rather than the size of any single year's return).

The fund has outperformed its benchmark in seven of the past eight calendar years, returning 108.92% over five years against 75.93% for the MSCI AC World index. The three-stage construction process — scoring, blending and risk-neutralising — is what produces returns with sufficient consistency to be meaningful rather than lucky.

Glossary of Investment Styles

Disclaimer

For fund distributors and professional investors only. Investing involves risk. The value of an investment and the income from it may fall as well as rise and investors might not get back the full amount invested. Past performance does not predict future returns. If the currency in which the past performance is displayed differs from the currency of the country in which the investor resides, then the investor should be aware that due to the exchange rate fluctuations the performance shown may be higher or lower if converted into the investor’s local currency. The views and opinions expressed herein, which are subject to change without notice, are those of the issuer companies at the time of publication. The data used is derived from various sources, and assumed to be correct and reliable at the time of publication. The conditions of any underlying offer or contract that may have been, or will be, made or concluded, shall prevail.

For investors in Europe (excluding Switzerland & the United Kingdom)

This is a marketing communication issued by Allianz Global Investors GmbH, www.allianzgi.com, an investment company with limited liability, incorporated in Germany, with its registered office at Bockenheimer Landstrasse 42-44, 60323 Frankfurt/M, registered with the local court Frankfurt/M under HRB 9340, authorised by Bundesanstalt für Finanzdienstleistungsaufsicht (www.bafin.de). Allianz Global Investors GmbH has established branches in France, Italy, Spain, Luxembourg, Sweden, Belgium  and the Netherlands. Contact details and information on the local regulation are available here (www.allianzgi.com/Info). The Summary of Investor Rights is available in English, French, German, Italian and Spanish at https://regulatory.allianzgi.com/en/investors-rights.

For investors in Switzerland

This is a marketing communication issued by Allianz Global Investors (Schweiz) AG, a 100% subsidiary of Allianz Global Investors GmbH. The Summary of Investor Rights is available in English, French, German, Italian and Spanish at https://regulatory.allianzgi.com/en/investors-rights.

For investors in the United Kingdom

This Fund is authorised overseas, but not in the United Kingdom. This fund is domiciled in Luxemburg and is authorised by the Commission de Surveillance du Secteur Financier (CSSF). The fund is recognised in the UK under the Overseas Funds Regime but is not a UK authorised fund. The fund is managed by Allianz Global Investors GmbH which is domiciled in Germany and is authorised by Bundesanstalt für Finanzdienstleistungsaufsicht (www.bafin.de). The Financial Ombudsman Service is unlikely to be able to consider complaints related to the scheme, its operator or its depositary. Investors in the United Kingdom can submit a complaint about any of the Funds, the Management