Explore research papers, case studies, and tools advancing ESG integration knowledge

A curated library of original research on cross-sectional ESG methodologies, factor performance, and implementation best practices.

Peer-reviewed methods
Documented assumptions
Practitioner-focused

Research library

Our research archive spans signal construction, factor purification, and live implementation. Each paper includes reproducible code, explicit assumptions, and honest discussion of limitations. We publish work that failed as readily as work that succeeded — because negative results shape better models.

Practical guidance for ESG practitioners

Data quality assessment, model calibration, and avoiding common ESG integration pitfalls

Audit vendor coverage gaps

Data

Before running a single regression, map which issuers lack ESG data and whether absence correlates with size, sector, or geography. Ignoring selection bias here invalidates every subsequent result.

Map coverage matrix Test selection bias Document exclusions
1 day
Easy

Test factor orthogonality

Modelling

ESG signals often load heavily on quality and low-volatility factors. Purify before attributing performance to sustainability — or risk celebrating a disguised value tilt.

Estimate loadings Construct residuals Validate out-of-sample
2 weeks
Medium

Model transaction costs

Implementation

A monthly-rebalanced ESG tilt with high turnover may underperform a slower-moving alternative after costs. Embed market-impact estimates directly into your optimisation.

Calibrate cost model Run pre-trade analysis Optimise rebalancing
3 weeks
Hard
Explore methodology details

ESG integration glossary

Comprehensive definitions of technical terms including cross-sectional regression, ESG alpha, factor crowding, and materiality mapping

Cross-sectional regression

Statistics
A statistical technique that estimates relationships by comparing many entities at a single point in time, revealing relative patterns rather than time-series trends.

ESG alpha

Performance

The incremental return attributed to environmental, social, and governance signals after controlling for traditional factor exposures and transaction costs.

Factor crowding

Risk
A condition where many market participants hold similar factor exposures, potentially eroding expected returns and amplifying drawdowns during liquidation.

Materiality mapping

Analysis

The process of identifying which ESG issues are financially relevant to a specific industry or issuer, distinguishing noise from information.

Look-ahead bias

Methodology
An error where a model uses information that would not have been available at the decision point, inflating backtested performance unrealistically.

Peer-relative scoring

Scoring
Normalising ESG metrics within comparable groups such as industry or region, accounting for structural differences in disclosure and business models.

Signal decay

Modelling

The rate at which a predictive factor loses its information content over time, informing optimal rebalancing frequency and holding periods.

Purified factor

Construction

An ESG signal with its overlap with traditional style factors removed, isolating the incremental information content for portfolio construction.

Monthly research briefs

Receive concise updates on cross-sectional ESG methodology, new factor research, and invitations to exclusive practitioner webinars. We send one email per month, never share your address, and you can leave anytime.

Cookie Preferences

Manage your cookie settings

We use cookies to improve your experience

This website uses cookies to enhance functionality, analyse traffic, and support our research communications. You can choose which categories to accept or reject below.

Essential cookies

These cookies are necessary for the website to function and cannot be disabled.

Performance cookies

These cookies help us understand how visitors interact with our research content.

For more information about how we handle your data, please review our Privacy Policy and Cookie Policy.

Privacy Policy