| ▲ | samfriedman a day ago |
| Accuracy is a useless statistic: give us precision and recall. |
|
| ▲ | henryl a day ago | parent | next [-] |
| Recall 91.5, F1 93.3 |
| |
| ▲ | paradite a day ago | parent [-] | | I think you need to define which one is the positive, and which one is the negative? Is AI generated code the positive? |
|
|
| ▲ | LPisGood a day ago | parent | prev [-] |
| Useless is perhaps a but harsh. It tells you something. |
| |
| ▲ | spott a day ago | parent | next [-] | | Only if you know the data distribution. It is pretty easy to get 99.99% accuracy on a dataset that is 99.99% a single class for example. | |
| ▲ | dymk a day ago | parent | prev [-] | | It tells me nothing because it doesn’t say if they mean precision or recall | | |
| ▲ | LPisGood a day ago | parent [-] | | It very much tells you something. Accuracy is a measure of overall correctness. Accuracy is something different than precision and recall. |
|
|