Type of Crime | Time Period | |||||||||
---|---|---|---|---|---|---|---|---|---|---|
1 Week | 2 Weeks | 1 Month | 2 Months | 3 Months | ||||||
PAI[1] | PEI*[2] | PAI | PEI* | PAI | PEI* | PAI | PEI* | PAI | PEI* | |
Student | ||||||||||
All Calls for Service | Warren | Yurick | Warren | Yurick | Warren | Yurick | Warren | Yurick | Yurick | Yurick |
Burglary | All[3] | All | All | All | Yurick | Ledray | Warren | Warren | Ledray | Ledray |
Street Crimes | Warren | Yurick | Warren | Yurick | Yurick | Warren | Warren | Warren | Warren | Yurick |
Theft of Auto | Warren | Warren | Warren | Scarborough | Warren | Yurick | Yurick | Warren | Yurick | Yurick |
Small Team/Business | ||||||||||
All Calls for Service | Tamer Zone |
William Herlands | Tamer Zone |
Intuidex | Tamer Zone |
Intuidex | Tamer Zone |
Intuidex | Tamer Zone |
Intuidex |
Burglary | Intuidex | Multiple winners[4] | Bates Analytics | Dylan Fitzpatrick | ANDY_NIJ | Bates Analytics | ANDY_NIJ | Bates Analytics | KUBQR1 | Bates Analytics |
Street Crimes | MURRAY MIRON | William Herlands | Tamer Zone |
Bates Analytics | Tamer Zone |
Intuidex | Tamer Zone |
Steven Yurick | Tamer Zone |
Center for Science and Law[5] / Steven Yurick |
Theft of Auto | pennaiken | CCC | pennaiken | TADIC | pennaiken | TADIC | Tamer Zone |
TADIC | KUBQR1 | PTL |
Large Business | ||||||||||
All Calls for Service | Codilime | Team Kernel Glitches | PASDA | Codilime | Codilime | Team Kernel Glitches | PASDA | Codilime | Codilime | Team Kernel Glitches |
Burglary | Team Kernel Glitches | Team Kernel Glitches | Team Kernel Glitches | Team Kernel Glitches | PASDA | IMPAQ | PASDA | IMPAQ | Jeremy Heffner | Codilime |
Street Crimes | Jeremy Heffner | GARANT Analytics | PASDA | Team Kernel Glitches | PASDA | Conduent Public Safety Solutions | PASDA | Codilime | PASDA | Codilime |
Theft of Auto | GRIER | Team Kernel Glitches | GRIER | Maruan Al-Sedivat | GRIER | GRIER | PASDA | Dataiku Inc | GRIER | Dataiku Inc |
Notes
[1](A) Prediction Accuracy Index (PAI)
- The PAI will measure the effectiveness of the forecasts with the following equation:
- Where n equals the number of crimes that occur in the forecasted area, N equals the total number of crimes, a equals the forecasted area, and A equals the area of the entire study area.
[2](B) Prediction Efficiency Index* (PEI*)
- The PEI* will measure the efficiency of the forecast with the following equation:
- Where PEI* equals the maximum obtainable PAI value for the amount of area forecasted, a. As such:
- Where n* equals the maximum obtainable n for the amount of area forecasted, a.
[3] There was a four-way tie in both PAI and PEI* scores for the one- and two-week burglary forecast — Warren, Yurick, Scarborough, and Ledray
[4] Multiple entrants tied in this category and timeframe: AltMaps CUDY, Dylan Fitzpatrick, GRANTHAM, INTUIDEX, KOONTZ, MURRAY MIRON, PTL, RAPTOR
[5] On December 13, 2017, the leaderboard was updated to include the Center for Science and Law in the Small Team/Business category winner for their top PEI* score for forecasting street crimes in the 3-month time period.