RPubs will retire in June 2027. Your existing documents will stay accessible through December 31, 2031
and Connect Cloud is the recommended home for new publishing. Read the blog post
gravatar

apurbasaha398

Apurba Saha

Recently Published

Predicting Daily Traffic Volume
For this project, traffic data for the years 2018 and 2019 was retrieved from the FHWA TMAS dataset. To enhance the analysis, additional features were created to capture time-series information, including day of the week, day of the month, month, long weekends, holidays, lags, and more. Traditional statistical time-series models like Linear regression, ETS (Error, Trend, Seasonality) and SARIMA (Seasonal Autoregressive Integrated Moving Average), ARIMAX, Decomposition were used to fit the data. A comparison between these models were made to identify which approach offers better predictive accuracy in terms of MAPE and RMSSE score. Finally, meaningful insights were derived from the time-series analysis that can help identify key factors influencing traffic volume.