Watch How to Generate a Baseline Portfolio Commentary With AI in 60 Seconds

Financial professionals who develop portfolio attribution summaries know it’s a time commitment to analyze data tables and charts and write the performance commentary from a blank page. That task has just become materially easier and faster through generative AI.

As the video highlights, when you click “Generate Commentary” for a report/timeframe you’ve defined within the Portfolio Analysis application of the FactSet Workstation, a Large Language Model will generate a baseline commentary in approximately 30-60 seconds. Statements and numbers in the commentary are linked to the source.

The commentary is an initial draft that you can copy/paste or download into a Word document to personalize with your perspective and tone. It includes four sections:

1. An executive summary of portfolio performance relative to your benchmark

2. A sub-period analysis of trends and persistence

3. A step-back explanation of relative portfolio performance against the benchmark and overperformance/underperformance for the groupings you want (e.g., sectors, regions, countries)

4. A step-in highlight of the most influential securities in the analysis along with aggregated news analysis

According to Chris Ellis, Executive Vice President, Head of Strategic Initiatives at FactSet, Portfolio Commentary could save you a meaningful amount of time.

“Based on internal testing, we anticipate this enhancement will enable asset managers, asset owners, and wealth managers to reduce the time spent writing portfolio commentary by a factor of eight and thus focus on the more high-value, strategic priorities of improving performance and strengthening client relationships.”

The release of Portfolio Commentary, our latest generative AI advancement, follows these additional AI capabilities:

• Transcript Assistant, our interactive, two-way chat solution for all firm types to extract the most salient points from earnings transcripts with users’ bespoke questions and pre-populated prompts. 

• FactSet Mercury, the beta release of a Large Language Model-based knowledge agent to support junior banker workflows and enhance fact-based decision making.

This blog post is for informational purposes only. The information contained in this blog post is not legal, tax, or investment advice. FactSet does not endorse or recommend any investments and assumes no liability for any consequence relating directly or indirectly to any action or inaction taken based on the information contained in this article.