Skip to content

This project applies time series forecasting to predict U.S. monthly traffic by state, comparing performance of Prophet, XGBoost, and SARIMAX models.

Notifications You must be signed in to change notification settings

pinstripezebra/Timeseries-Forecasting

Repository files navigation

Timeseries analysis of traffic data

This project applies time series forecasting methods to model U.S. monthly traffic data between 2019 and 2023.

The data for this project is aggregated from the US Federal Highway Administration (link here: https://www.fhwa.dot.gov/policyinformation/travel_monitoring/tvt.cfm)

Approaches Taken

There are 3 main notebooks here:

  1. initial_exploration: contains initial exporation and EDA of the data
  2. overview_prophet: an approach to modeling the data using Facebooks Prophet library
  3. overview_xgboost: an approach to modeling the data using the XGBoost library

About

This project applies time series forecasting to predict U.S. monthly traffic by state, comparing performance of Prophet, XGBoost, and SARIMAX models.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published