Corporate Relative Valuation Using Heterogeneous Multi-Modal Graph Neural Network

Corporate relative valuation (CRV) refers to the process of comparing a company’s value from company products, core staff and other related information, so that we can assess the company’s market value, which is critical for venture capital firms. Traditional relative valuation methods heavily rely on tedious and expensive human efforts, especially for non-publicly listed companies. However, the availability of information about company’s invisible assets, such as patents, talent, and investors, enables a new paradigm to learn and evaluate corporate relative values automatically. Indeed, in this paper, we reveal that, the companies and their core members can natually be formed as a heterogeneous graph and the attributes of different nodes include semantically-rich multi-modal data, thereby we are able to extract a latent embedding for each company. The network embeddings can reflect domain experts’ behavior and are effective for corporate relative valuation. Along this line, we develop a heterogeneous multi-modal graph neural network method, named HM
$^{2}$
, which deals with embedding challenges involving modal attribute encoding, multi-modal aggregation, and valuation prediction modules. Specifically, HM
$^{2}$
first performs the representation learning for heterogeneous neighbors of the input company by taking relationships among nodes into consideration, which aggregates node attributes via linkage-aware multi-head attention mechanism, rather than multi-instance based methods. Then, HM
$^{2}$
adopts the self-attention network to aggregate different modal embeddings for final prediction, and employs dynamic triplet loss with embeddings of competitors as the constraint. As a result, HM
$^{2}$
can explore companies’ intrinsic properties to improve the CRV performance. Extensive experiments on real-world data demonstrate the effectiveness of the proposed HM
$^{2}$
.