{"resourceId":"crime-science-chicago-predictive-policing-data-incompleteness-20261014","versions":[{"version":"external-b94a0f6529916f1322fdde17e640df47a1513b240b2d653702fe72ec0cd8e333","resource":{"id":"crime-science-chicago-predictive-policing-data-incompleteness-20261014","title":"Crime Science study using Chicago 2022–2024 records finds incomplete crime data can create or worsen ethnic disparities in predictive policing outputs, with the largest shifts for Black-majority communities","organization":"Mengqin K. Jiang, Federico Liberatore and Alun Preece (authors); Crime Science (Springer Nature)","sector":"Policing / predictive policing and data quality","geography":"Chicago, Illinois, United States (method transferable; single-city results)","publishedAt":"Published: 14 October 2026; Crime Science volume 15, article 40","publicationDate":"2026-10-14","eventDate":null,"sourceName":"Crime Science (Springer Nature)","sourceLabel":"How crime data incompleteness shapes ethnic disparities in predictive policing: evidence from Chicago","sourceUrl":"https://link.springer.com/article/10.1186/s40163-026-00306-9","evidenceClass":"academic-research","outcomeClass":"cautionary","topics":["data-security","governance-procurement","knowledge-work"],"finding":"Using Chicago crime records (2022–2024), census data and the HAGEN spatio-temporal model, the authors removed records at controlled rates (25–100% in low-diversity neighbourhoods; 50% or 100% in single-ethnicity-majority communities) and allocated prediction errors to groups as predicted over-policing (false positives) and under-policing (false negatives). Removing records from a group’s majority communities generally reduced predicted over-policing and increased predicted under-policing for that group, with Asian-majority scenarios an exception. The largest shifts came from removing data in Black-majority communities; in the appendix, predicted under-policing for Black residents rose by 58.36% from 0% to 100% reduction. The authors call for auditing missingness and its demographic distribution before deploying event-level predictive policing.","sledRelevance":"Agencies buying forecasting, hot-spot or resource-allocation analytics rarely audit where their records are missing. This study gives a concrete, testable reason to require data-completeness audits by neighbourhood before deployment, and it reinforces that model accuracy alone does not guarantee fair or effective outcomes.","evidence":"Opened the open-access article and read the abstract, methods, results, discussion and limitations. Outcomes are model-based proxies, not observed police behaviour; missingness was simulated by uniform random removal within targeted communities; one city, one period, one model. The article also cites a randomised trial in Montevideo finding no significant crime-reduction benefit from a predictive policing system over analysts.","architectureImplications":"Interpretation: analytics pipelines should report data completeness by geography and group, and test model outputs under plausible missingness before release.","governanceImplications":"The authors frame missingness auditing as a prerequisite for deploying event-level predictive policing.","securityPrivacyImplications":"Disparity risk arises from data gaps (under-reporting, uneven detection, recording practices), not only from model design.","caveats":"Simulation on one city and one model; recorded crime treated as proxy for crime; random within-area removal does not model real under-reporting; baseline data already incomplete; results may differ by season and crime type.","streamIds":["public-safety"],"roles":{"sales":"Sales framing: police analytics are only as fair as the records feeding them, and this peer-reviewed Chicago study shows data gaps can shift predicted over- and under-policing sharply between groups. The bounded offer is a data-completeness and disparity audit before or during an analytics deployment. The study cannot support claims about actual police behaviour or crime reduction from any product.","engineering":"Engineering framing: pre-sales should ask how the agency’s forecasting or allocation model handles missing records, whether completeness is measured by neighbourhood, and whether error rates are reported by group. Proof should rerun the agency’s model under controlled data removal, as the study did, and compare false-positive and false-negative allocation across communities.","delivery":"Delivery framing: the work is a repeatable completeness and disparity check built into analytics release. Dependencies include access to model outputs, census data and analyst time. The owner is the crime analysis unit with oversight review. Acceptance should be a documented audit with disparity thresholds agreed in advance, not a single accuracy score."},"roleDetails":{"sales":{"customerProblem":"Agencies using predictive or allocation analytics cannot show whether data gaps skew outputs against particular communities.","stakeholders":["Crime analysis manager","Deputy chief for operations","Oversight board or inspector general","City data officer","Community advisory group"],"discoveryQuestions":["Which analytics drive deployment decisions today?","Is record completeness measured by neighbourhood?","Are false positives and negatives reported by area or group?","Has the vendor done disparity testing?"],"valueHypothesis":"A completeness and disparity audit can identify where analytics outputs are unreliable before they shape deployment.","potentialEngagement":"6-week data-completeness and disparity audit of one analytics product using the agency’s own records.","unsupportedClaims":["Effects on actual policing behaviour","Crime reduction from predictive policing","Results generalize beyond Chicago and HAGEN"]},"engineering":{"fit":"Agencies using spatio-temporal forecasting, hot-spot or resource-allocation analytics.","architectureIntegration":"Add completeness metrics and controlled-missingness tests to the analytics pipeline, with neighbourhood-level error allocation using census data.","prerequisites":["Access to model outputs and training data","Census or demographic data at neighbourhood level","Analyst capacity"],"constraints":["Vendor models may be opaque","Real missingness mechanisms unknown","Small areas produce noisy estimates"],"security":"Handle incident-level data under existing CJIS and records rules; publish only aggregated results.","proofOfValue":["Proposed: replicate controlled data removal on the agency model","Proposed: report predicted over/under-policing allocation by community before and after"]},"delivery":{"work":"Build and run a completeness and disparity audit and embed it in model release and annual review.","dependencies":["Vendor cooperation","Demographic data","Oversight body engagement"],"ownership":"Crime analysis unit with inspector general or oversight review","skillsAdoption":"Train analysts on missingness assessment and on communicating model limits to command staff.","governanceCheckpoints":["Pre-deployment audit","Annual disparity review","Public summary to oversight body"],"acceptanceCriteria":["Proposed: completeness measured for every neighbourhood","Proposed: disparity thresholds defined and tested before release"],"risks":["Vendor refuses access to model","Audit used to justify rather than question deployment","Simulation assumptions misread as real-world effects"]}},"retrievedAt":"2026-10-20T02:52:44Z","enrichedAt":"2026-10-20T02:58:42Z","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Interpretation: crime analysts need skills to assess record completeness and explain model limits to commanders.","procurementImplications":"Interpretation: buyers should require vendors to provide disparity testing under data-incompleteness scenarios and neighbourhood-level error reporting.","operatingModelImplications":"Interpretation: crime analysis units, not vendors alone, should own completeness audits and periodic disparity reviews.","sourceVerification":{"openedUrl":"https://link.springer.com/article/10.1186/s40163-026-00306-9","referenceExcerpt":"The findings motivate auditing missingness and its demographic distribution as a prerequisite for deploying event-level PP systems.","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}