Beat the Warning Lights

Investors often ask how it’s possible to allocate capital to European stocks given the political risks that abound. We think the answer is to combine disciplined stock picking with risk-management tools that look for unintended threats to a portfolio.

Questions like these peaked at the height of the European debt crisis in 2011. Today, these questions are being asked again with urgency given uncertainty over Brexit, Italian politics and the European growth outlook, as well as potential fallout from trade wars, turmoil in emerging markets and the global growth outlook.

Managing Risk in Stock Selection

Risk can mean many different things to different investors. For some it’s just another word for volatility. For others it’s all about how a portfolio looks versus a benchmark.

We believe managing risk is about ensuring that a portfolio’s returns are driven primarily by the business strengths of its holdings. That means making sure performance isn’t knocked off course—or even boosted unexpectedly—by events or exposures that aren’t related to the businesses.

The first step in effective fundamental risk management is to understand what could go wrong at the company level. Thorough company-level and industry research is essential, for example, to determine how sensitive company earnings are to changes in the macroeconomic environment and to identify environmental, social or governance risks that could damage performance.

But even the best company analysts may have blind spots. So challenging our own perspectives is important. In some cases, this can be done by engaging with short sellers, typically working at hedge funds. Since short sellers are trying to profit from a stock price falling, they have a negative opinion on the company’s prospects. By talking with them, long investors can identify potential holes in a thesis. This can lead us to revisit key assumptions or to revise our return forecasts to compensate for risks that we may not originally have spotted.

Innovation in Understanding Portfolio-Level Risk

At the portfolio level, equity fund managers typically rely on a range of quantitative risk models from external providers to test a portfolio’s resilience to various hazards. Models that analyze a portfolio’s likely response to different scenarios can help control exposures, though ultimately they aren’t a substitute for experience and judgement.

Equity fund managers typically also rely on risk models that test a portfolio’s exposure to known country, industry and factor risks. These can gauge how cheap or expensive, or how large or small, are the portfolio companies relative to their broad investment universe. Risks that don’t fit into these buckets are then categorized as stock-specific risk.

But these traditional risk models might need some help. While it’s important to understand and control factor exposures, which can have a big impact on performance, this approach on its own may be too static and simplistic. Many other risks aren’t stock-specific but don’t necessarily fit easily into standard risk categories. And the way different stocks are exposed to these risks can vary significantly over time.

Cluster Analysis Fills the Gaps

Cluster risk analysis is a good supplement to traditional risk tools. This technique seeks correlated sources of risk that might not be obvious to quantitative risk models or fundamental analysts.

How does it work? Cluster analysis is an artificial intelligence technique that segments stocks into groups whose returns have been moving closely together over the past few months. For example, it can help separate groups of stocks within an industry or subindustry that will benefit in a risk-on trade, when markets reward riskier assets, and others that might be more aligned with a risk-off environment.

The findings can defy conventional wisdom. For example, while industrials are generally seen as risk-on stocks, some companies in the sector have business models that make them more defensive. In contrast, healthcare is often seen as a defensive sector, but some drugmakers with a small number of products or imminent patent expiries, might be much less defensive than perceived.

Discovering Surprising Correlations

Cluster analysis can reveal surprising patterns. For example, we have recently found similar return patterns from a select group of technology, industrial, materials and chemical companies. The reasons for these correlations are not always obvious. But even without an explanation, identifying the correlation can help a portfolio manager avoid too much exposure to an unidentified risk.

In another case last year, we found a curious change in the trading patterns of a UK water utility. In the past, this stock behaved in line with its utility peers, which are typically considered defensive. At some point, it started trading in line with UK retailers, which are much more cyclical. A possible explanation? The shift might have been related to the rise of the Labour Party in UK polls, as the party has a stated policy of nationalizing assets like water utilities. This potential disruption could greatly widen the range of possible outcomes for the stock. Whatever the reason, the utility’s risk profile had changed significantly, which should prompt a rethink of its role as defensive ballast for a portfolio.

Finding new ways to detect unintended risks before the warning lights flash is paramount. Systematic cluster analysis can help investors connect changing return patterns of stocks with external risks such as trade wars or Brexit, that might go undetected by common risk-management tools. Engaging with short sellers can sharpen fundamental research. Adding these two techniques to more traditional risk models can upgrade risk management in a European equity portfolio today and help investors construct a portfolio with truly idiosyncratic return streams, that are unlikely to be knocked off course by adverse political or macroeconomic developments.