Searching for Alpha with Textual Data

In the asset management arena, interest continues to grow in harnessing unstructured data, such as transcripts from corporate earnings calls, to identify differentiated sources of alpha.^[1] The advent of machine learning (ML) capabilities, such as natural language programming (NLP), is making it possible to easily assess large volumes of unstructured textual data to uncover new insights. In fact, analysis by S&P Global Market Intelligence has shown that NLP-driven Textual Data Analytics used with earnings call transcripts can provide additional stock selection power, which is complementary to the existing analytics commonly used by institutional portfolio managers today.^[2] S&P Global worked with a large global hedge fund that continuously looks for new developments that can further enhance its investment management capabilities and generate alpha for its clients. The firm, focused on both quantitative and fundamental strategies, looked to S&P Global’s growing Textual Data Suite as a source for alpha generation and strategy differentiation.