Host: The Japanese Society for Artificial Intelligence
Name : The 33rd Annual Conference of the Japanese Society for Artificial Intelligence, 2019
Number : 33
Location : [in Japanese]
Date : June 04, 2019 - June 07, 2019
In this paper, we try to analyze relationships between mission statements and protability. The mission statements are very important messages for companies, because they include founders' spirits, the business policies and so on. Therefore, we consider that mission statements affect protability. Mission statements and protability (The Return On Asset (ROA) was used) were gathered from annual securities reports because descriptions are accurate and reports are easy to obtain. As mission statements were written in natural language and data to be analyzed becomes complicated, a neural computational method called `potential learning' which can interpret internal representations was used. As a result, we found that a generalization performance of the model was 0.6125 (accuracy) and mission statements composed of multiple messages may affect ROA.