What is it about?
Competitor identication is an essential component of corporate strategy. With the rapid development of articial intelligence, various data mining methodologies and frameworks have emerged to identify competitors. In general, the competitiveness among companies is determined by both market commonality and resource similarity. However, because resource information is more diffcult to obtain than market information, existing studies primarily identify competitors via market commonality. To address this limitation, we introduce multisource company descriptions as well as heterogeneous business relationships, and propose a novel method for simultaneously mine the market commonality and resource similarity.
Photo by Alina Grubnyak on Unsplash
Why is it important?
We provide a new perspective to identify competitive companies by considering market commonality and resource similarity. Here, we transform the heterogeneous business relationships into a HBN and model the competitor identication problem as a link prediction problem. With that, a multilevel graph attention network is proposed to predict competitive companies. Subsequential, we conduct a series of experiments to verify the effectiveness of our proposed model for competitor prediction.
Read the Original
This page is a summary of: A multisource data fusion-based heterogeneous graph attention network for competitor prediction, ACM Transactions on Knowledge Discovery from Data, September 2023, ACM (Association for Computing Machinery),
You can read the full text:
The following have contributed to this page