The National Institute of Justice’s “Recidivism Forecasting Challenge” aims to increase public safety and improve the fair administration of justice across the United States. The Challenge aims to improve the ability to forecast recidivism using person- and place-based variables with the goal of improving outcomes for those serving a community supervision sentence. Results from the Challenge will provide critical information to community corrections departments that may help facilitate more successful reintegration into society for previously incarcerated persons and persons on parole.
There are three submission deadlines under the Challenge:
- Submission period 1: May 31, 2021, 11:59:59 pm ET
- Submission period 2: June 15, 2021, 11:59:59 pm ET
- Submission period 3: June 30, 2021, 11:59:59 pm ET
Awards
Number of Awards: 27
Total Amount Awarded: $723,000
NIJ Recidivism Forecasting Challenge Winner: Team TrueFit
NIJ Recidivism Forecasting Challenge Winner: Team VT-ISE
NIJ has updated the Challenge to:
- Add missing deadlines under section X: Other Rules and Conditions.
- Provide a sample submission file.
- Updated the scoring section by adding:
If an applicant fails to provide a probability for an individual in the test dataset it will be considered an incorrect forecast (i.e., if the individual did recidivate, it will be scored as though you forecasted a 0 probability; and, if the individual did not recidivate, it will be scored as though you forecasted a 1 probability). - Correct incorrect variable names in the data file:
- _v1 becomes Prior_Arrest_Episodes_PPViolationCharges
- _v2 becomes Prior_Conviction_Episodes_PPViolationCharges
- _v3 becomes Prior_Conviction_Episodes_DomesticViolenceCharges
- _v4 becomes Prior_Conviction_Episodes_GunCharges
NIJ Has updated the Challenge to clarify:
- That the team roster must include to which category the submitter is applying
- What files types are allowable.