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? 
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?
| № | Пользователь | Рейтинг |
|---|---|---|
| 1 | Benq | 3676 |
| 2 | Kevin114514 | 3659 |
| 3 | jiangly | 3640 |
| 4 | turmax | 3450 |
| 5 | tourist | 3408 |
| 6 | strapple | 3360 |
| 7 | Um_nik | 3354 |
| 8 | squareOf105 | 3348 |
| 9 | maroonrk | 3312 |
| 10 | idontwannadothis…e | 3191 |
| Страны | Города | Организации | Всё → |
| № | Пользователь | Вклад |
|---|---|---|
| 1 | Qingyu | 155 |
| 2 | nik_exists | 151 |
| 3 | maspy | 149 |
| 4 | AmShZ | 145 |
| 5 | Um_nik | 143 |
| 6 | Errichto | 139 |
| 7 | BledDest | 136 |
| 8 | adamant | 135 |
| 9 | maroonrk | 132 |
| 10 | cry | 130 |
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.