沒有偏見的演算法?

Image Not Showing Possible Reasons
  • The image file may be corrupted
  • The server hosting the image is unavailable
  • The image path is incorrect
  • The image format is not supported
Learn More →

Who am I?

  • 黃柏愷
  • BK_0710@NCTU
    Image Not Showing Possible Reasons
    • The image file may be corrupted
    • The server hosting the image is unavailable
    • The image path is incorrect
    • The image format is not supported
    Learn More →
  • Reinfor Learning

Image Not Showing Possible Reasons
  • The image file may be corrupted
  • The server hosting the image is unavailable
  • The image path is incorrect
  • The image format is not supported
Learn More →

Image Not Showing Possible Reasons
  • The image file may be corrupted
  • The server hosting the image is unavailable
  • The image path is incorrect
  • The image format is not supported
Learn More →

Image Not Showing Possible Reasons
  • The image file may be corrupted
  • The server hosting the image is unavailable
  • The image path is incorrect
  • The image format is not supported
Learn More →

Image Not Showing Possible Reasons
  • The image file may be corrupted
  • The server hosting the image is unavailable
  • The image path is incorrect
  • The image format is not supported
Learn More →

NORTHPOINTE 的聲明

Image Not Showing Possible Reasons
  • The image file may be corrupted
  • The server hosting the image is unavailable
  • The image path is incorrect
  • The image format is not supported
Learn More →
　　
Image Not Showing Possible Reasons
  • The image file may be corrupted
  • The server hosting the image is unavailable
  • The image path is incorrect
  • The image format is not supported
Learn More →
　　
Image Not Showing Possible Reasons
  • The image file may be corrupted
  • The server hosting the image is unavailable
  • The image path is incorrect
  • The image format is not supported
Learn More →

預判再犯律

👱🏻‍♂️ 35%

👱🏿‍♂️ 60%

Machine Bias

| 黑人被告 | 總人數 |
|:––––:|:–––:|:–––:|:–––:|
| 再犯 | 1901 |
| 未再犯 | 1714 |
| 總人數 | 3615 |

| 白人被告 | 總人數 |
|:––––:|:–––:|:–––:|:–––:|
| 再犯 | 966 |
| 未再犯 | 1488 |
| 總人數 | 2454 |

黑人被告 高風險 低風險 總人數
再犯 1369 532 1901
未再犯 805 990 1714
總人數 2174 1522 3615

FP Rate: 44.85% FN Rate: 27.99%

白人被告 高風險 低風險 總人數
再犯 505 461 966
未再犯 349 1139 1488
總人數 854 1600 2454
FP Rate: 23.45% FN Rate: 47.72%

👱🏿‍♂️　　　　　　　👱🏻‍♂️
　　　　　　
判刑過長　　　　逍遙法外再犯

data source

👱🏿‍♂️　　　　　　👱🏻‍♂️
PPV 0.63　　　　PPV 0.59
NPV 0.65　　　　NPV 0.71

Jon Kleinberg 的證明

根據 Jon Kleinberg 的證明兩個群體不可能在沒有校準偏誤的情形下，又擁有相同的 false negative 跟 false positive 發生率。因此除非黑人與白人的犯罪率相同，我們才能開發出完美公平的演算法。


LINK

Thanks!

Select a repo