Manulife Refines ESG Methodology and Plugs Data Gaps with NLP

The asset manager has adopted materiality tools, industry handbooks, and NLP techniques to help navigate ESG data limitations. 

In the absence of standards, it’s better to do it yourself. Many asset managers have taken this approach as they try to cull insights from noisy environmental, social, and governance (ESG) data, and develop their own sustainable investment frameworks.

Manulife has spent the last two years fine-tuning its ESG methodology for investing in equities and fixed income. In that time, the global investment firm has been trying to integrate ESG principles into all parts of its investment processes—from how it sources ESG data, to incorporating it into its valuation models, to security selection, portfolio construction, and risk management.

Like many asset managers struggling to navigate the ESG space, Manulife has developed and adopted several proprietary ESG tools, including materiality maps and industry handbooks.

The internal handbooks have been curated to outline ESG sub-categories and sub-sectors that are most relevant to the companies in the portfolios, for both short- and long-term investing, and highlight how they effect a company’s financial materials.

“What we mean by financially material are [the ESG themes or factors] most likely to pose a financial risk or opportunity to the company,” Eric Nietsch, head of ESG in Asia at Manulife, tells WatersTechnology. “That’s where the industry handbooks come in. We have what we call materiality maps for identifying what are the most important ESG sub-topics for different industries.”

In other words, the industry sub-groups are mapped to ESG-related shocks or business opportunities associated with the companies’ financial materials, including operations, reputation, market access, innovation, and regulatory compliance. 

Another area we are exploring is using NLP for analytics that allows us to quickly find ESG news and get a sense of the implications.
Eric Nietsch

For instance, poor governance could result in ESG shocks like labor stoppages or supply-chain disruption, which have a knock-on effect on material aspects like product releases, revenues, or operational costs. In other cases, social factors, like negative health and safety reports, or environmental issues like high carbon emissions can have a direct impact on a company’s reputation and potentially lead to downstream expenses such as regulatory fines or court claims. Manulife’s Asia fixed income team also leverages in-house ESG scorecards, which rate ESG ratings bonds.

But applying ESG principles to the nuts and bolts of the investment cycle doesn’t go far enough, Nietsch says. Some investment firms, including Manulife, claim to play a “stewardship role” in offering companies in their portfolios guidance on what investors are demanding, and how to manage their ESG profiles better. Yet it is unclear how effective these meetings with senior executives are in shaping the way they manage their firms.

“It’s important that it doesn’t stop there, that once we make the decision to invest, we’re continuing to actively vote our proxies if it’s an equity strategy, or engage with the companies that were invested in to encourage them to manage some of the relevant environmental or social risks, and take advantage of opportunities that are available to them,” Nietsch says.

The Yardstick

Measuring ESG factors is not an exact science or easily quantifiable. Not every ESG theme has metrics or performance figures to substantiate an investment theory, Nietsch says. For themes like diversity or inclusion, portfolio managers may have to apply a qualitative approach to analyzing ESG data—for instance, predicting how a board composition might impact a company’s performance.

Integrating ESG is also challenged by the separation between the E, S, and G components, which can be uncorrelated. In some cases, a company may have a low carbon footprint, yet have a poor reputation for diversity and inclusion. Deciding which factors take precedence can become a balancing act.

“You could have a company that has a business line with a strong growth opportunity, but it has a rising cost base or declining margins,” Nietsch says. “There could be multiple ESG issues to consider, where a company has those same growth opportunities, but maybe has a relatively weaker governance structure. So you would have to balance those in the research and in the [investment] approach.”

Manulife’s ESG methodology is informed by sell-side research, data vendors, third-party ESG ratings, internal work, and the Sustainability Accounting Standards Board’s sector-based model. The asset manager pulls in ESG ratings, research, and data from MSCI, Morningstar’s Sustainanalytics, Bloomberg, and FactSet. For specific datasets, it uses S&P’s TruCost and MSCI’s Carbon Delta for analytics on environmental or climate-related issues.

ESG data can be scattered and unstructured, making it a nightmare to draw insights from or use it to support traditional forms of information. In some cases, the data is unavailable due to scanty company disclosures or insufficient data quality. To tackle this issue, Manulife has turned to natural language processing.

The investment manager’s ESG teams use AlphaSense, a provider of market intelligence and NLP solutions, to round out or map its ESG data. Nietsch says that the technology is used to complement its existing datasets by pulling in textual information from traditional and alternative sources, to create a coherent ESG signal.

“One way that we can use it is to try to fill in the gaps where the information is not provided,” he adds. “Another area we are exploring is using NLP for analytics that allows us to quickly find ESG news and get a sense of the implications.”

Only users who have a paid subscription or are part of a corporate subscription are able to print or copy content.

To access these options, along with all other subscription benefits, please contact info@waterstechnology.com or view our subscription options here: http://subscriptions.waterstechnology.com/subscribe

You are currently unable to copy this content. Please contact info@waterstechnology.com to find out more.

Most read articles loading...

You need to sign in to use this feature. If you don’t have a WatersTechnology account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an individual account here