Skip to content

Latest commit

 

History

History
21 lines (17 loc) · 1.06 KB

README.md

File metadata and controls

21 lines (17 loc) · 1.06 KB

NRC Classification Using Logistics Regression, Random Forest Classifier, and CNN

Motivation

The National Response Center (NRC) receives calls whenever there is an oil spill, chemical spill, or HAZMAT (hazardous material) release. Depending on the characteristics of the incident that caused the release, a DOT PHMSA 5800 incident report may need to be completed. A 5800 HAZMAT incident is a more speciic and more dangerous type of incident.

The purpose of this exercise is to create a model that can predict whether or not an NRC incident will require a 5800 report to be generated.

By knowing whether or not a 5800 report will need to be created, the data science team at PHMSA can reduce the latency of generating incident details to management by as much as 30 days.

Report Sections

  • Exploratory Data Analysis
  • Train and Test
    • Logistic Regression
    • Random Forest Classifier
    • Convolutional Neural Network (CNN)
  • Head-to-Head Comparison
  • Conclusions and Next Steps