Dataset

Credit

Borrower-month observations from a credit panel, with synthetic regressors and outcome added for benchmarking.

Bipartite incidence pattern for Credit

Graph Summary

A comparatively well-connected real panel; useful for baseline timing.

The primary benchmark graph is built from unique (id1, id2) pairs. The figure shows a binned sparsity pattern of the bipartite incidence block, with both partitions relabeled to contiguous integer identifiers. This block is the off-diagonal part of the corresponding graph Laplacian.

516,810rows
516,810unique edges
13,946id1 levels
140id2 levels
1components
14,086nodes

Variables

Columns in the clean CSV:

id1 id2 ruc t x1 x2 y

The v1 graph uses id1 and id2. Additional identifier-like columns available for richer specifications: ruc, t.

Source Notes

Borrower-period credit panel collected by the author.

Identifiers are anonymized; regressors and outcome are synthetic benchmark variables.

Historical Benchmark

2017 SEC benchmark timings for this dataset, in seconds:

MethodCitationSeconds
MAP-Aitken (Guimaraes 2012) 15.1
MAP-SD (Gaure 2013) 20.5
MAP-CG-Sym (Correia 2016) 14.2
MAP+Prune (Correia 2016) 28.2
LSMR (Gomez 2016) 17.3