| Deep Learning vs Bryan | 371–421 | 46.84% |
| Deep Learning vs Kazuya | 340–392–1 | 46.45% |
| Deep Learning vs Dragunov | 318–316 | 50.16% |
| Deep Learning vs Steve | 270–343 | 44.05% |
| Deep Learning vs Asuka | 272–261 | 51.03% |
| Deep Learning vs Hwoarang | 240–267 | 47.34% |
| Deep Learning vs Jin | 238–264 | 47.41% |
| Deep Learning vs Paul | 238–250 | 48.77% |
| Deep Learning vs King | 255–228 | 52.80% |
| Deep Learning vs Feng | 239–211 | 53.11% |
| Deep Learning vs Heihachi | 215–216 | 49.88% |
| Deep Learning vs Victor | 213–216–1 | 49.65% |
| Deep Learning vs Law | 222–188 | 54.15% |
| Deep Learning vs Reina | 205–187 | 52.30% |
| Deep Learning vs Jack-8 | 175–209 | 45.57% |
| Deep Learning vs Yoshimitsu | 197–170 | 53.68% |
| Deep Learning vs Lee | 192–174 | 52.46% |
| Deep Learning vs Lili | 165–195 | 45.83% |
| Deep Learning vs Lars | 186–162 | 53.45% |
| Deep Learning vs Leroy | 183–158 | 53.67% |
| Deep Learning vs Devil Jin | 141–191 | 42.47% |
| Deep Learning vs Jun | 179–144 | 55.42% |
| Deep Learning vs Lidia | 153–161 | 48.73% |
| Deep Learning vs Azucena | 161–139 | 53.67% |
| Deep Learning vs Claudio | 125–169 | 42.52% |
| Deep Learning vs Alisa | 153–113 | 57.52% |
| Deep Learning vs Armor King | 127–137 | 48.11% |
| Deep Learning vs Clive | 136–123 | 52.51% |
| Deep Learning vs Xiaoyu | 122–135 | 47.47% |
| Deep Learning vs Shaheen | 119–133 | 47.22% |
| Deep Learning vs Raven | 128–123 | 51.00% |
| Deep Learning vs Nina | 106–132–1 | 44.54% |
| Deep Learning vs Eddy | 102–114 | 47.22% |
| Deep Learning vs Leo | 104–106 | 49.52% |
| Deep Learning vs Zafina | 87–113 | 43.50% |
| Deep Learning vs Kuma | 75–73 | 50.68% |
| Deep Learning vs Fahkumram | 89–59 | 60.14% |
| Deep Learning vs Anna | 68–75 | 47.55% |
| Deep Learning vs Miary Zo | 72–69 | 51.06% |
| Deep Learning vs Panda | 35–44 | 44.30% |
Limitations
This data is often requested to give insight into which characters you have more trouble with than others, but it is not particularly helpful for that. The main issue is that it is heavily skewed by how strong the opponents you play are.
For example, this data suggests my worst matchup is clearly vs Reina, but that's just because most of those games are vs Yagami.
There is a way to account for this being worked on. The central idea is to assign each matchup a rating vs you which adjusts based on the result, much like the regular rating but also based on the rating of each player. With this, it would give a better summary of how well you perform vs each character.
In the meantime, this page is here to present the data as requested.