Citation Analysis – Machine Learning with High-Cardinality Categorical Features \\ in Actuarial Applications

Machine Learning with High-Cardinality Categorical Features \\ in Actuarial Applications
Benjamin Avanzi, Greg Taylor, Melantha Wang, Bernard Wong
https://arxiv.org/abs/2301.12710

Citation mentions

Cited references

Sections

6,081

Words (approx)

References by Citation Intensity

Ordered by composite index (descending). Higher values indicate more intensive citation.

#	Mentions	Breadth	Sec. Wtd	Share	Composite	Main %
1	7	6	13.0	0.090	1.000	100%
2	4	4	6.5	0.051	0.843	75%
3	4	2	8.0	0.051	0.811	100%
4	2	2	4.0	0.026	0.644	100%
5	2	2	4.0	0.026	0.644	100%
6	2	2	4.0	0.026	0.644	100%
7	2	2	4.0	0.026	0.644	100%
8	2	2	4.0	0.026	0.644	100%
9	2	2	4.0	0.026	0.644	100%
10	2	2	4.0	0.026	0.644	100%
11	2	2	4.0	0.026	0.644	100%
12	3	2	4.5	0.038	0.644	67%
13	3	1	6.0	0.038	0.585	100%
14	2	2	2.5	0.026	0.511	50%
15	2	2	2.5	0.026	0.511	50%
16	1	1	2.0	0.013	0.406	100%
17	1	1	2.0	0.013	0.406	100%
18	1	1	2.0	0.013	0.406	100%
19	1	1	2.0	0.013	0.406	100%
20	1	1	2.0	0.013	0.406	100%
21	1	1	2.0	0.013	0.406	100%
22	1	1	2.0	0.013	0.406	100%
23	1	1	2.0	0.013	0.406	100%
24	1	1	2.0	0.013	0.406	100%
25	1	1	2.0	0.013	0.406	100%
26	1	1	2.0	0.013	0.406	100%
27	1	1	2.0	0.013	0.406	100%
28	1	1	2.0	0.013	0.406	100%
29	1	1	2.0	0.013	0.406	100%
30	1	1	2.0	0.013	0.406	100%
31	1	1	2.0	0.013	0.406	100%
32	1	1	2.0	0.013	0.406	100%
33	1	1	2.0	0.013	0.406	100%
34	1	1	2.0	0.013	0.406	100%
35	1	1	2.0	0.013	0.406	100%
36	1	1	2.0	0.013	0.406	100%
37	1	1	2.0	0.013	0.406	100%
38	1	1	2.0	0.013	0.406	100%
39	1	1	2.0	0.013	0.406	100%
40	1	1	2.0	0.013	0.406	100%
41	1	1	2.0	0.013	0.406	100%
42	1	1	2.0	0.013	0.406	100%
43	1	1	2.0	0.013	0.406	100%
44	1	1	2.0	0.013	0.406	100%
45	1	1	2.0	0.013	0.406	100%
46	1	1	0.5	0.013	0.087	0%
47	1	1	0.5	0.013	0.087	0%
48	1	1	0.5	0.013	0.087	0%
49	1	1	0.5	0.013	0.087	0%
50	1	1	0.5	0.013	0.087	0%
51	1	1	0.5	0.013	0.087	0%
52	1	1	0.5	0.013	0.087	0%

Reference

Year

Mentions

Breadth

Sec. Wtd

Composite

Main %

13.0

0.090

1.000

100%

6.5

0.051

0.843

75%

8.0

0.051

0.811

100%

4.0

0.026

0.644

100%

4.0

0.026

0.644

100%

4.0

0.026

0.644

100%

4.0

0.026

0.644

100%

4.0

0.026

0.644

100%

4.0

0.026

0.644

100%

4.0

0.026

0.644

100%

4.0

0.026

0.644

100%

4.5

0.038

0.644

67%

6.0

0.038

0.585

100%

2.5

0.026

0.511

50%

2.5

0.026

0.511

50%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

2.0

0.013

0.406

100%

0.5

0.013

0.087

0.5

0.013

0.087

0.5

0.013

0.087

0.5

0.013

0.087

0.5

0.013

0.087

0.5

0.013

0.087

0.5

0.013

0.087

Measures: Mentions = total in-text citations; Breadth = distinct sections; Sec. Wtd = section-weighted count (body ×2, lit review/appendix ×0.5); Share = mentions / total citations in paper; Composite = geometric mean of normalised count, breadth, and main-text ratio; Main % = fraction of mentions in main text (excl. appendix). (self) = self-citation.