Predictive Analytic Services

Predictive analytics, aka machine learning or artificial intelligence, is using statistical models to predict the probability of a future event occurring, or forecast a numeric value that is likely to occur in the future. Examples are predicting the number of crimes likely to occur in an area in the future or predicting the probability an individual is going to be involved in gun violence in the next year.

These are not like predictions in Minority Report, they do not call for preemptively arresting people before they have committed a crime, but uses different proactive tactics to prevent crime before it occurs.

CRIME De-Coder has extensive experience in predictive analytics, has published several papers and won multiple prediction competitions (NIJ recidivism forecasting, NASA Algae Bloom).

Spatial Based Forecasts

CRIME De-Coder has published several models to forecast the most concentrated areas of crime (Wheeler & Reuter, 2021; Wheeler & Steenbeek, 2021; Yoo & Wheeler, 2019). Below is an example million dollar hotspot in Dallas using the methodology CRIME De-Coder developed (Wheeler & Reuter (2021):

Million Dollar Hotspot

Person Based Predictions

Examples of person based forecasting are chronic offender systems (Wheeler et al., 2019), and personal risk assessments for parole or bail (Circo & Wheeler, 2022). Chronic offender systems are used by police departments and prosecutors offices to identify individuals to target specialized services. Personal risk assessments are commonly used to assign individuals certain levels of parole supervision, or identify individuals of low risk to release on their own recognizance.

Time Series Forecasting

Time series forecasting is the use of historical data to forecast the number of events likely to occur in the future. CRIME De-Coder has developed methodology to forecast rare crime data (Wheeler & Kovandzic, 2018; Yim et al., 2020), and actively monitor crime patterns to identify spikes that may demand police response (Wheeler, 2016).

Homicide Forecast Outlier

Fair Application of Predictive Analytics

One critique of predictive analytics is that machine learning is racist. This is misleading – predictive policing is a method to identify areas or people that can benefit the greatest from specific interventions. CRIME De-Coder has developed methodology to make predictive analytics more fair and racially equitable (Circo & Wheeler, 2022; Wheeler, 2020).

A small number of places or people cause the most crime. Targeting resources to those highest risk people and places, in the most fair way possible, is the best approach to tackle difficult crime and violence problems in communities.

If you are interested in predictive analytics, contact the CRIME De-Coder today for a free consultation to discuss your agencies needs.

References