Events

Special Achievement in GIS Award

2017 SAG Award Winners

State of Indiana, Management and Performance Hub

View Photo(s) of Award Presentation

Project Goal

o The Indiana Daily Crash Prediction Map was built to bring awareness to specific areas of risk on Indiana’s roadways and reduce first responder response time to accidents. The map is a tool which offers the public and first responders information on high risk areas that they can build into their daily routines.
Learn more about us
Learn more about our application: Site 1 | Site 2

Business Problem Solved

o Roadway fatalities were up across the nation starting in 2014. In Indiana, we saw a rise of 7.5% in roadway fatalities from 2014-2015. In response, the Indiana State Police partnered with the Management Performance Hub to combat the problem through the use of data.

Technology Implemented

o The initial development of the map consisted of a two month discovery phase in which the Management Performance Hub (MPH) evaluated data sets across the state. Data was evaluated on availability, completeness, and significance in the predictive model. After the discovery phase and completion of the predictive model, MPH began building the map using Esri tools with the assistance of consultants from the EAP program. ArcGIS 10.4 was used to build the map and ArcGIS online is used to host the map.

Development Team Biography

Major Mike White, Indiana State Police - Executive project sponsor who initiated the predictive crash tool project.
First Sergeant Rob Simpson, Indiana State Police - Served as the project lead from the Indiana State Police.
Captain Larry Jenkins, Indiana State Police - Assisted with outreach officer adoption of the tool.
Ashley Schenck, Management Performance Hub Project Director - MPH project lead responsible for overseeing development and user experiences.
Suri Mareddy, Management Performance Hub ETL Developer - Led the integration of data sources and automation of data updates.
Dan LaBar, KSM Consulting Data Scientist - Led the development of the data models and predictive algorithms.

Contact Us |  Privacy |  Legal |  Site Map