AI Case Study
JPMorgan Chase Research improves long/short performance by up to 0.5% by identifying sentiment and locating idiosyncratic risk in news items
JPMorgan filters news content using machine learning and natural language processing (NLP) to identify sources of asset idiosyncratic risk which allows them to avoid potential shorts. This has reportedly avoided up to 8 potential shorts per year.
Investment Banking And Investment Services
JPMorgan developed Newsfilter, a tool which "sifts through hundreds of news sources received through providers including Bloomberg and FactSet, along with wider unstructured data each day, using a recurrent neural network that is continuously trained by manually labelled data to pick up patterns that distinguish M&A-related news articles from others. 'The tool is useful in removing potential sources of idiosyncratic risk,' says Yazann Romahi, chief investment officer of QBS at the firm. This is useful in the rumor-mired world of M&A".
"A key strategy in JPMorgan Asset and Wealth Management’s Quantitative Beta Strategies (QBS) team lies in event-driven investing, specifically in systematically investing in M&A deals, alongside equity long/short strategies. But the team struggled with sifting the wheat from the chaff in the vast volume of information that it consumed every day."
JP Morgan claims that the machine-learning enhancements have improved performance in long/short by up to 0.5 percent per year, by filtering out and avoiding up to eight potential shorts per year.
"NewsFilter picks up words from unstructured news articles in free text format and filters out uninformative components, forming a domain-specific vocabulary and transforming the input into a structured form. We use a distributed representation to translate the words in the text to predictive features. This allows semantically similar words to cluster in a high-dimensional space. In addition, we initialize our deep-learning process with pre-trained vector embeddings to leverage the rich semantic domain knowledge captured by large studies carried out on billions of news items and Wikipedia articles".