Data scientists at Deutsche Bank have developed an artificial intelligence tool that cuts through the flannel padding out the Environmental Social and Governance reports of most companies to analyse non-financial news and quantify the stock impact.
Deutsche Bank's Alpha-Dig machine is one of the first products developed by the Bank's Data Innovation Group (dbDIG), which was set up to tap into the power of alternative data and AI to provide data-driven investment solutions.
The bank trained A-Dig on data from 1000 organisations, using Natural Language Processing to infer the context of a typical ESG report and generate 'buy' and 'sell' signals accordingly.
The tool is being used to cut through the positive spin and upbeat language that clutters company financial reporting and dig out the hidden meanings behind the 'greenwashing'. The Bank says that over the years since the financial crisis, the average number of words per quarterly SEC filing is now about 20,000, more than double the number two decades ago, and annual filings have grown to 50,000 words.
Deutsche believes that traditional systems that aggregate key words and then assign scores to stocks are no longer fit for purpose, "yet investors persist with these systems as a human simply cannot read the millions of pages of information available".
A-Dig - first unveiled in April this year - has been designed specifically to overcome these limitations, cross-referencing the hidden context buried in company's non-financial discslosures alongside actual news reports and general market sentiment to generate Alpha.
Andy Moniz, Deutsche's chief data scientist explains further:
A more detailed description of the A-Dig effect on stock picking is available in the latest issue of the Bank's inhouse magazine Konzept