Lazy Network: A Word Embedding-Based Temporal Financial Network to Avoid Economic Shocks in Asset Pricing Models

Table 4

Factor exposures of the portfolio that uses closeness centrality: the factor loadings of the long-only portfolio that goes long on the 50 companies with the lowest closeness centrality in the Lazy Network.

Factors	Equally weighted		Value-weighted
	3-factor	5-factor	3-factor	5-factor
Intercept (α) t-stat	0.70 (3.80)	0.72 (3.97)	0.90 (4.14)	0.92 (4.22)
MKTRF t-stat	0.97 (21.71)	0.90 (18.92)	0.87 (16.55)	0.81 (14.30)
SMB t-stat	0.52 (7.28)	0.52 (7.40)	-0.03 (-0.35)	-0.03 (-0.30)
HML t-stat	0.26 (4.38)	0.24 (3.99)	0.17 (2.32)	0.15 (2.01)
UMD t-stat	—	-0.13 (-3.41)	—	−0.11
PS_VWF t-stat	—	0.07 (1.32)	—	0.06 (0.97)

The t-statistics are in parentheses and displayed under the estimates. , , The significance at the 1%, 5%, and 10% levels, respectively.