| Keyser Soza vs Jin | 31–31 | 50.00% |
| Keyser Soza vs Armor King | 24–36 | 40.00% |
| Keyser Soza vs King | 28–27 | 50.91% |
| Keyser Soza vs Steve | 33–20 | 62.26% |
| Keyser Soza vs Hwoarang | 25–22 | 53.19% |
| Keyser Soza vs Reina | 27–19 | 58.70% |
| Keyser Soza vs Kazuya | 19–26 | 42.22% |
| Keyser Soza vs Law | 21–18 | 53.85% |
| Keyser Soza vs Lili | 22–17 | 56.41% |
| Keyser Soza vs Lee | 17–17 | 50.00% |
| Keyser Soza vs Eddy | 26–8 | 76.47% |
| Keyser Soza vs Paul | 15–18 | 45.45% |
| Keyser Soza vs Bryan | 20–12 | 62.50% |
| Keyser Soza vs Dragunov | 19–12 | 61.29% |
| Keyser Soza vs Xiaoyu | 18–12 | 60.00% |
| Keyser Soza vs Azucena | 16–14 | 53.33% |
| Keyser Soza vs Heihachi | 11–19 | 36.67% |
| Keyser Soza vs Asuka | 21–7 | 75.00% |
| Keyser Soza vs Lars | 13–13 | 50.00% |
| Keyser Soza vs Yoshimitsu | 14–11 | 56.00% |
| Keyser Soza vs Jun | 16–7 | 69.57% |
| Keyser Soza vs Miary Zo | 11–12 | 47.83% |
| Keyser Soza vs Feng | 8–13 | 38.10% |
| Keyser Soza vs Devil Jin | 9–11 | 45.00% |
| Keyser Soza vs Lidia | 11–5 | 68.75% |
| Keyser Soza vs Victor | 8–7 | 53.33% |
| Keyser Soza vs Leo | 9–3 | 75.00% |
| Keyser Soza vs Leroy | 4–8 | 33.33% |
| Keyser Soza vs Raven | 5–6 | 45.45% |
| Keyser Soza vs Anna | 5–5 | 50.00% |
| Keyser Soza vs Alisa | 6–3 | 66.67% |
| Keyser Soza vs Nina | 3–6 | 33.33% |
| Keyser Soza vs Zafina | 4–4 | 50.00% |
| Keyser Soza vs Jack-8 | 5–2 | 71.43% |
| Keyser Soza vs Claudio | 3–2 | 60.00% |
| Keyser Soza vs Shaheen | 4–1 | 80.00% |
| Keyser Soza vs Kuma | 2–3 | 40.00% |
| Keyser Soza vs Fahkumram | 0–4 | 0.00% |
| Keyser Soza vs Panda | 2–1 | 66.67% |
| Keyser Soza vs Clive | 3–0 | 100.00% |
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.