AI Case Study
Nomura Asset Management quantify news sources as positive or negative to aid analysts in investment decisions using natural language processing
NAM conducted a POC using natural language processing to analyse data from a variety of non-traditional sources (e.g. Twitter) to quantify as positive and negative sentiments regarding investments. The result was the ability to quantify information that data analysts tend to interpret as qualitative and supplementary.
Fund And Asset Management
"The objective of the PoC was to assess whether analysis with AI would contribute to increased accuracy of portfolio managers' investment decision-making. Portfolio managers at asset management firms usually have to process and analyze a large amount of information which includes not only analyst reports, but also a flood of various news sources, industry blogs and social media, such as Twitter®, to make forecasts and determine the impact on stock prices. This PoC is one of the first full-scale efforts made by a Japanese asset manager to analyze and score analyst reports using AI."
"Nomura Asset Management Co., Ltd. (NAM), one of Japan's leading investment managers, and Nomura Research Institute, Ltd. (NRI), a leading provider of consulting services and system solutions, today announced that they have conducted a proof of concept study to examine natural language processing utilizing Artificial Intelligence."
"The result of the PoC highlighted that analysis of analyst reports using AI enabled the quantitative assessment of information which portfolio managers usually see as qualitative. In addition, even text information from news websites and blogs could be quantitatively scored and used to enhance the ability of portfolio managers to make investment decisions. In the future, it is expected that more information that could not have been captured by humans qualitatively, will be available as quantitative information and utilized for investment decision-making."
The technology assisted review works "to analyze all the information a portfolio manager would consume and score them into two groups; either positive (indicating that company performance or corporate value is likely to rise) or negative (indicating these factors are likely not to rise)... NRI first conducted a natural language analysis on analyst reports which highlighted the shifts of investment decisions (For example, a shift from neutral to overweight or from neutral to underweight). The language patterns for "positive" and "negative" were then identified and used as training data for AI. Finally, the AI calculated the similarities between the training data and the targeted materials, scoring whether each piece of information is "positive" or "negative"."
Text data from analyst reports, social media, industry blogs, etc.