Interactive Document Intelligence for ESG

The goal of this plug and play solution is to automatically consolidate unstructured documents into a unified, searchable and thematically categorized database, leverage sentiment analysis to accelerate analysis, and provide end users with an interactive dashboard to analyze their document corpus all within Dataiku.  More details on the specifics of the solution can be found on the knowledge base. This solution is only available on installed instances.

Business Overview

Inflows in ESG products have increased by 140% in 2020 to represent above $40 trillion assets.  The move to ESG is accelerated by the surge in regulation impacting all players across the value chain combined with a growing number of large-scale industry initiatives such as the Net Zero Banking Alliance launched by the UN in 2021. 

The data sources required to effectively embed ESG into financial processes, including KYC, trade finance, credit scoring, and investments, are many and varied. The ability to leverage unstructured data through document intelligence is critical. Currently, organizations rely on individuals to read sections of these documents, or search for relevant materials without a systematic way of categorizing and understanding the data.

This solution automatically consolidates unstructured document data into a unified, searchable and automatically categorized database, with insight accessible via a powerful and easy to use dashboard. Using a modular ESG keyword database (which can be enhanced or swapped out for other topics with ease) the solution can be  used to tackle questions such as: 

• What ESG topics are being addressed within a portfolio or document collection, and which are rarely tackled?
• What firms or offerings are facing challenges or successes associated with ESG topics of interest, e.g., relating to environmental impact?
• What documents or entities are ESG outliers according to my document collection, positive and negative?
• What ESG trends emerge over time around topics and firms associated with them?

Highlights

• Rapid time-to-insight using an interactive, purpose-built dashboard showing high level trends via time series and peer group comparison, alongside drill downs to underlying documents, all without needing technical knowledge.
• Discover ‘clusters’ of words that form around specific topics of interest via topic analytics, revealing new insights and perspectives.
• Easily and quickly adjust core components to suit the needs and preferences of the business, whether technical or topic focused, thanks to the highly customizable and modular design.

Modular, reusable and customizable pipeline

Automatically digitize documents, extract text, and consolidate data into a unified and searchable database. The solution operates out of the box with ESG topic modeling and SEC 10Ks but can be quickly and easily adjusted to suit your own needs, data, and preferred OCR tool.

Explore !

Topic Analytics

The topic dashboard allows a user to discover the ‘clusters’ of words that form around specific ESG topics of interest within the documents provided, revealing new insights and perspectives.

Explore !

Interactive insight on firms of interest

Users are able to search a company name and select an ESG category (or multiple categories) to analyze the results of the document intelligence pipeline.

Explore !

Direct access to text of interest

Drill down into ESG sub-categories to observe the extracted windows from the document as well as the sentiment score and analyze results alongside the original document.

Explore !

Time series and peer group comparison

The time series frequency analysis dashboard enables business users to track the frequency of key words and sentiment overtime across ESG topics. A user can also see how a specific company compares to its peer group.

Explore !