12 June 2024 in IEEE Transactions on Computational Social Systems
Finding potential successful startups is always a key issue for industrial innovation and economic development, yet it poses a significant challenge due to the complexity of investments and low success rates. Compared with existing models on knowledge correlations among pairwise startups in a first-order perspective, potential dependencies among sequential investment behaviors reveal knowledge correlations among multiple startups, which requires modeling from a higher order perspective. In this article, a novel higher order network (HON) framework, generated by dependencies among investment behaviors with timestamps, is proposed to identify the pattern of knowledge flows among startups, which has been approved higher accuracy in predicting investment behaviors. Moreover, we introduce a HON-based centrality indicator to measure the importance of startups. Experiments compared with baseline models have shown that the startups identified by proposed indicator are more influential in knowledge propagation and are closer to success. An empirical study conducted by Crunchbase database further reveals that internet-based startups occupy a significant position in investment landscapes, with those associated with finance and commerce not only attracting considerable investments but also facilitating greater success for related startups.
24 November 2023 in arXiv
Link prediction -- to identify potential missing or spurious links in temporal network data -- has typically been based on local structures, ignoring long-term temporal effects. In this chapter, we propose link-prediction methods based on agents' behavioral synchrony. Since synchronous behavior signals similarity and similar agents are known to have a tendency to connect in the future, behavioral synchrony could function as a precursor of contacts and, thus, as a basis for link prediction. We use four data sets of different sizes to test the algorithm's accuracy. We compare the results with traditional link prediction models involving both static and temporal networks. Among our findings, we note that the proposed algorithm is superior to conventional methods, with the average accuracy improved by approximately 2% - 5%. We identify different evolution patterns of four network topologies -- a proximity network, a communication network, transportation data, and a collaboration network. We found that: (1) timescale similarity contributes more to the evolution of the human contact network and the human communication network; (2) such contribution is not observed through a transportation network whose evolution pattern is more dependent on network structure than on the behavior of regional agents; (3) both timescale similarity and local structural similarity contribute to the collaboration network.
8 April 2024 in International Journal of Modern Physics C