Applied Data Analytics training program – High Need Populations (2017)
The Coleridge Initiative's Applied Data Analytics training program focused on high need populations.
Class Overview and Projects
The Coleridge Initiative Applied Data Analytics Training Program is designed to equip public policy professionals with advanced computer science and data science skills. The program provides a hands-on introduction to data analytics topics ranging from basic SQL and Python coding to running and interpreting machine learning models. Application to real-world issues is key to the organization of the program – the present Training Program addressed High Need Populations.
During the program, participants were grouped into teams in which they scoped and executed a project related to Criminal Justice and Recidivism, Access to Transportation, and/or Social Benefits. All teams presented their results on February 7th and 8th, 2018. Project themes included:
- Predicting Recidivism: Using machine learning techniques, several teams identified key factors in re-incarceration using social, economic, and demographic variables. The results provide valuable insight for targeted interventions on high need individuals.
- Impact of Social Benefits: Other groups measured whether TANF benefits have a positive impact on the economic or criminal outcomes of those who enroll. These projects provide quantifiable impact evaluations of the policy, according to several outcome measures.
- Access to Public Services: Another series of projects looked at the access of high-need populations to public services. By visualizing the distribution of transportation, public health, or education, these projects are relevant to decision-makers in charge of territorial organization.
Data Available for Class
For both class notebooks and team projects, participants of the Applied Data Analytics Training Program have access to several datasets, including confidential micro-data hosted on the secure Administrative Data Research Facility platform. The datasets available for the High Need Populations Training Program included:
- Illinois Department of Human Services (IDHS) data
- Illinois Department of Employment Services (IDES) data
- Illinois Department of Corrections (IDOC) data: exit data, parole data
- Department of Housing and Urban Development (HUD) program data
- Census LEHD Origin-Destination Employment Statistics (LODES)
Day 1: Introduction, Core Datasets & Git
Day 2: SQL & Databases
Day 3: Python for Data Analysis
Day 4: Record Linkage
Day 5: Visualization & APIs
Day 6: Network Analysis
Day 7: Introduction to Machine Learning
Day 8: Machine Learning
Day 9: Text Analysis
Day 10: Web Scraping
Day 11: Inference & Big Data
Day 12: Privacy & Confidentiality