Kenkoooo's AtCoder problem recommendation has columns for solve probability and median solve time. I understand that solve probability is computed using the user's internal Elo, but how does kenkoooo estimate median solve time? 
→ Pay attention
→ Top rated
| # | User | Rating |
|---|---|---|
| 1 | jiangly | 4039 |
| 2 | tourist | 3841 |
| 3 | jqdai0815 | 3682 |
| 4 | ksun48 | 3590 |
| 5 | ecnerwala | 3542 |
| 6 | Benq | 3535 |
| 7 | orzdevinwang | 3526 |
| 8 | gamegame | 3477 |
| 9 | heuristica | 3357 |
| 10 | Radewoosh | 3355 |
→ Top contributors
| # | User | Contrib. |
|---|---|---|
| 1 | cry | 169 |
| 2 | -is-this-fft- | 165 |
| 3 | atcoder_official | 160 |
| 3 | Um_nik | 160 |
| 5 | djm03178 | 158 |
| 6 | Dominater069 | 156 |
| 7 | adamant | 153 |
| 8 | luogu_official | 152 |
| 9 | awoo | 151 |
| 10 | TheScrasse | 147 |
→ Find user
→ Recent actions
Codeforces (c) Copyright 2010-2025 Mike Mirzayanov
The only programming contests Web 2.0 platform
Server time: Jan/22/2025 17:59:00 (l1).
Desktop version, switch to mobile version.
Supported by
You can try to read the source code: github.com/kenkoooo/AtCoderProblems
In particular, the solve time is computed here in atcoder-problems-frontend/src/utils/ProblemModelUtil.ts, which seems like a linear function of your rating times
problemModel.slopeplusproblemModel.intercept. These two parameters are computed from a simple linear regression on participants' ratings and their solve time of the problem, not particularly sure about this but you can take a look at the time-estimator folder and function.py.