Orange County, Fla.

The Markup and Gizmodo have obtained and analyzed actual predictions for more than three dozen departments that used PredPol predictive policing software for at least six months between 2018 and 2020. This data sheet provides the findings from our disparate impact analysis and public housing analysis for Orange County, Fla. To learn more about the project read, our investigation. For more details on how we did this analysis, read our methodology.

Findings

Overview

  • Predpol’s algorithm relentlessly targeted the block groups in each jurisdiction that were most heavily populated by people of color and the poor, particularly those containing public housing. The algorithm spared block groups with more White residents the same level of scrutiny.

  • The proportion of each jurisdiction’s Black and Latino residents was higher in the most-targeted block groups and lower in the least-targeted block groups compared to the jurisdiction overall. The opposite was true for the White population: The least-targeted block groups contained a higher proportion of White residents, and the most-targeted block groups contained a lower proportion.

  • For the majority of jurisdictions in our data set (27 jurisdictions), a higher proportion of their low-income households lived in the block groups that were targeted the most. In some jurisdictions, all of their subsidized and public housing was located in block groups PredPol targeted more than the median.

  • These vast disparities were caused by the algorithm relentlessly predicting crime in the block groups in each jurisdiction that contained a higher proportion of the low-income residents and Black and Latino residents. They were the subject of crime predictions every shift, every day, and in multiple locations in the same block group.

  • We also analyzed arrest statistics by race from the FBI’s Uniform Crime Reporting (UCR) Project for 29 of the agencies in our data that were in UCR. In 90 percent of them, per capita arrests were higher for Black people than White people—or any other racial group included in the dataset, mirroring the characteristics of the neighborhoods that the algorithm targeted.

  • We analyzed arrest data provided by 10 law enforcement agencies in our data and the rates of arrest in predicted areas remained the same whether PredPol predicted a crime that day or not.

Race and Ethnicity

Compared to Orange County, Fla., overall, the most-targeted block groups had:

  • A greater proportion of Asians residents.
  • A greater proportion of Black residents.
  • A smaller proportion of Latino residents.
  • A smaller proportion of White residents.

Compared to Orange County, Fla. overall, the least-targeted block groups had:

  • A smaller proportion of Asian residents.
  • A smaller proportion of Black residents.
  • A smaller proportion of Latino residents.
  • A greater proportion of White residents.

Targeting Level Demographic Proportion of Block Group pop.
Most Targeted Block Groups Asian 3.7
Most Targeted Block Groups Black 23.8
Most Targeted Block Groups Latino 22.8
Most Targeted Block Groups White 31.6
Median Targeted Block Groups Asian 2.6
Median Targeted Block Groups Black 9.3
Median Targeted Block Groups Latino 21.4
Median Targeted Block Groups White 49.0
Least Targeted Block Groups Asian 0.3
Least Targeted Block Groups Black 7.6
Least Targeted Block Groups Latino 8.8
Least Targeted Block Groups White 61.6
Jurisdiction Total Asian 2.6
Jurisdiction Total Black 14.6
Jurisdiction Total Latino 25.4
Jurisdiction Total White 37.9

Household Income

Compared to Orange County, Fla. overall, the most-targeted block groups had:

  • A greater proportion of households that made less than $45K a year.
  • A smaller proportion of households that made between between $75K and 100k a year.
  • A smaller proportion of households that made between $120k and 150K a year.
  • A smaller proportion of households that made $200K and above a year.

Compared to the Orange County, Fla. overall, the least-targeted block groups had:

  • A smaller proportion of households that made less than $45K a year.
  • A smaller proportion of households that made between $75K and 100K a year.
  • A smaller proportion of households that made between $120K and 150K a year.
  • A smaller proportion of households that made $200K and above a year.

Targeting Level Demographic Proportion of Block Group pop.
Most Targeted Block Groups $120k - 150k 1.3
Most Targeted Block Groups $75k - 100k 6.1
Most Targeted Block Groups $200k and above 2.9
Most Targeted Block Groups Less than 45k 40.9
Median Targeted Block Groups $120k - 150k 1.7
Median Targeted Block Groups $75k - 100k 7.1
Median Targeted Block Groups $200k and above 4.4
Median Targeted Block Groups Less than 45k 29.3
Least Targeted Block Groups $120k - 150k 1.2
Least Targeted Block Groups $75k - 100k 3.2
Least Targeted Block Groups $200k and above 2.9
Least Targeted Block Groups Less than 45k 30.0
Jurisdiction Total $120k - 150k 1.9
Jurisdiction Total $75k - 100k 6.7
Jurisdiction Total $200k and above 3.1
Jurisdiction Total Less than 45k 32.1

Public Housing

In Orange County, Fla. 15 percent of public housing was on block groups the software targeted the most, 67 percent of public housing was on block groups the software targeted more than the median.

The table below provides how many predictions each block with public housing received. The final column tells us the percentage of days a block received predictions from PredPol’s software between Feb 23, 2018 and Sep 30, 2020. We confirmed these dates with the Orange County, Fla., police department.

Census GEOID Block Predictions Num. Public Housing Units Pct. days w/ Predictions
120950171032 2028 5585 2 99.8948475
120950149041 1003 4573 1 99.5793901
120950152021 1029 3560 1 97.7917981
120950149041 1001 3817 1 96.0042061
120950121001 1002 2769 1 94.2166141
120950149042 2000 2216 1 93.4805468
120950152021 1011 2153 2 92.6393270
120950171081 1001 3394 1 92.0084122
120950167271 1000 3213 3 91.0620400
120950169071 1007 1537 2 87.3817035
120950170172 2001 2179 1 85.4889590
120950122011 1000 1372 1 81.9137750
120950123041 1031 1224 1 81.2828601
120950152023 3024 1349 2 79.2849632
120950132021 1005 1759 1 78.3385910
120950167291 1022 1268 1 70.4521556
120950145021 1045 1055 3 66.8769716
120950169041 1000 923 1 66.7718191
120950123041 1029 979 1 60.5678233
120950145031 1004 726 1 54.2586751
120950176002 2066 644 1 50.9989485
120950151062 2003 720 1 47.7392219
120950124011 1019 565 1 46.6876972
120950187002 2032 477 16 42.1661409
120950164071 1031 422 1 34.0694006
120950136061 1024 498 1 31.6508938
120950167291 1058 399 1 31.4405889
120950148051 1010 314 1 31.3354364
120950178071 1000 359 1 26.7087277
120950167241 1030 411 2 24.6056782
120950142001 1002 302 1 20.6098843
120950170131 1023 255 1 20.1892744
120950151041 1027 261 14 18.9274448
120950167341 1048 194 1 18.4016824
120950167241 1010 237 1 18.0862250
120950167291 1041 292 1 17.5604627
120950135051 1027 194 2 16.6140904
120950185001 1049 126 1 12.5131441
120950167131 1001 150 1 11.7770768
120950187002 2035 115 1 10.7255521
120950176001 1054 161 1 10.6203996
120950167141 1006 103 1 9.7791798
120950168061 1018 120 2 9.5688749
120950135112 2000 96 1 9.4637224
120950167321 1071 150 1 9.1482650
120950123072 2000 89 1 8.9379600
120950175011 1090 87 23 8.5173502
120950124021 1001 82 1 5.1524711
120950170141 1062 67 1 4.9421661
120950167291 1059 50 1 4.8370137
120950169071 1016 42 1 4.4164038
120950135051 1029 33 1 3.3648791
120950165041 1018 36 1 3.1545741
120950134051 1016 47 1 2.6288118
120950169031 1031 22 2 1.8927445
120950169041 1026 24 1 1.8927445
120950170081 1090 16 1 1.4721346
120950164111 1017 13 1 1.3669821
120950187002 2033 14 22 1.3669821
120950171031 1044 12 1 1.2618297
120950187003 3005 14 2 1.2618297
120950116002 2010 14 1 1.1566772
120950167121 1052 9 1 0.9463722
120950124021 1014 10 2 0.9463722
120950168061 1116 7 1 0.7360673
120950177031 1035 5 1 0.5257624
120950187002 2038 4 1 0.4206099
120950169032 2000 3 6 0.3154574
120950117013 3008 2 14 0.2103049
120950180002 2017 2 3 0.2103049
120950164101 1026 1 1 0.1051525

Maps

Predictions

Density Map

The map below aggregates all the predictions Orange County, Fla., received in our analysis window into a 2D grid. Each square of the grid represents an area approximately 500 ft. x 500 ft., the size of the PredPol prediction box. The color represents the number of predictions that occurred within the square. The more predictions, the darker the square.

Prediction Count Description
0 - 640 Least Predictions
640 - 1280
1280 - 1920
1920 - 2560
2560 - 3190
3190 - 3840 Most Predictions

Sources: Markup, Predpol

The grid drawn on this map provides an approximate aggregation of the prediction data. The actual prediction box in the reports provided to departments will vary from the ones shown above.

Choropleth

This map shows the predictions aggregated to the level of the Census block group. Aggregating prediction data to the geographic area of a Census block group introduces additional complexity to the analysis, and hence this map should be interpreted with some caution. See the limitations section of the methodology for more details.

Source: Markup, Predpol

Race and Ethnicity

Black

Source: 2018 five-year ACS.

Latino

Source: 2018 five-year ACS.

White

Source: 2018 five-year ACS.

Household Income

Less than $45k

Source: 2018 five-year ACS.

$75k - $100k

Source: 2018 five-year ACS.

$125k - $150k

Source: 2018 five-year ACS.

$200k and above

Source: 2018 five-year ACS.

Methods

We analyzed the distribution of PredPol predictions for Orange County, Fla. at the geographic level of a Census block group, which is a cluster of blocks with a population of between a few hundred to a few thousand people, generally. There are 375 block groups in Orange County, Fla., the smallest block group had a population of approximately 0 and the largest had a population of approximately 31,938.

In Orange County, Fla., we analyzed 796,885 predictions and used there locations to determine the block groups that were targeted the most, the median and the least. This data sheet presents the breakdown of the racial groups and household income ranges of the people who lived in those block groups. We also present the breakdowns for Orange County, Fla. overall for comparison. The predictions we analyzed were between Feb 23, 2018 and Sep 30, 2020 , we received confirmation that Orange County, Fla. department used the software between Dec 20, 2017 and Sep 30, 2020.

For the race/ethnicity and income analyses, we merged 2018 five-Year American Community Survey data and prediction data and observed the makeup of block groups that were targeted above and below the median, those targeted the most and those targeted the least. For the sake of consistency in our analysis we only used demographic groups for which we had reliable population estimates for all the jurisdictions in our data set. These are:

  • Racial Groups
    • Black
    • Asian
    • Latino
    • White
  • Household Income
    • Less than $45K
    • Between $75K-$100K
    • Between $125K-$150K
    • Greater than $200K

Definitions

We used the Census’ “designated place” boundaries as the boundaries for most jurisdictions. For Sheriff’s departments we confirmed the boundaries with the department.

We defined the most-targeted block groups as those in Orange County, Fla. which encompassed the highest five percent of predictions. We defined the median-targeted block groups as the five percent around the median block group for predictions. And we defined the least-targeted block groups as those with the bottom five percent of predictions.

In some of the larger jurisdictions, more than five percent of block groups got zero predictions. In those cases, we chose the most populated block groups with no predictions for the five percent. Learn more about how we did this in our methodology.

We identified public housing through HUD’s online lookup tool available at https://resources.hud.gov

Data

The data used to generate this analysis can be found in our GitHub repository. It also contains the URLs for the rest of the data sheets from our analysis.