Due to a significant increase in the number of automobiles, traffic congestion has become a serious issue in recent years. This paper discusses various techniques for forecasting traffic flow to resolve the issue of traffic congestion. To begin, we will demonstrate how time series can be applied in this field. Second, we will attempt to describe which time-series models will be most beneficial in resolving the most pressing issue. Following that, we'll compare the results obtained using various methods using accuracy parameters. Additionally, we observe that the ARIMA time series forecasting method is incapable of producing appropriate results due to the seasonality observed in the data. We discovered in this research paper that the SARIMA time series forecasting method produces more accurate results when forecasting traffic flow at 15-minute and 30-minute intervals. Additionally, we discovered that for short time intervals, i.e., one minute, FBProphet outperforms SARIMA.

Keywords : Traffic time-series, ARIMA, SARIMA, Facebook Prophet, Traffic Prediction