Supervisors’ Influence within the Chicago Police Department

Part I: Who are supervisors?

Figure 1: Supervisors with complaint percentiles above 75. The y axis is the individual supervisor’s ID and the x axis is the complaint percentile, from 75–99.
Figure 2: Units whose supervisors are above the 75th complaint percentile. The y axis is unit ID and the x axis is complaint percentile, from 75 to 99.
Figure 3: A still image of the bubble chart showing unit size and complaint percentile. The values are the unit ID. The size of the bubble is an indication of how many officers are in that unit. The color red indicates if a unit’s supervisor has a complaint percentile above 75. Upon hovering over the bubbles, you can see the unit’s average complaint percentile.

Part II: What is their influence?

Figure 4: A still image of our degree analysis on the accusals data. Large nodes denote supervisors. Colors denote different units. Upon hovering, the officer’s ID, unit, and complaint percentile are shown.
Figure 5: PageRank results from the accusals network. These are the 10 most influential individuals according to PageRank. They are all supervisors. Notice the complaint percentiles are not in line with our other findings.

Part III: How much are problematic supervisors costing the city?

Figure 6: Results of the total_cost (the sum of fees_cost and payment) in descending order for the 30 supervisors payment data is available for.
Figure 7: Units and their average settlements cost (ave_cost) and total cost (total_cost) in descending order by average cost. These are the top 10 most costly units when sorting by average cost.

Part IV: Predicting Future Misconduct and Cost

Figure 8 (left): A linear distribution in complaint percentile data. Supervisor complaint percentile on the x axis, and average unit complaint percentile on the y axis. Figure 9 (right): A linear distribution in unit settlements data. Average unit settlements cost on the y axis and average unit complaint percentile on the x axis.

Conclusion

Future Research

Our work:

The authors:

--

--

--

Software engineer and graduate student studying AI at Northwestern. Talking too much to my dog. Being a “cool” aunt. I like knowing things. She/Her

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Aligning Data Virtualization, Streaming, and ETL

Why Use Excel and Why Not

Drawing maps with custom shapes in Google Slides

Labeling Data with Haystack Annotation Tool

What I’ve Learned In 2 Year 9 Month as A Data Engineer

Round Dollar Value Stability Analysis

Flight from the Cities?

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
KJ Schmidt

KJ Schmidt

Software engineer and graduate student studying AI at Northwestern. Talking too much to my dog. Being a “cool” aunt. I like knowing things. She/Her

More from Medium

Pump it up — How to deal with missing data?

Regression [With Code]: A Lighthouse for Data Scientists

Importing Inquisit data files into SPSS

Learning journey 08/02/2022

t-SNE on MNIST data-set