Artificial intelligence (AI) has a broad range of applications in enhancing the efficacy, efficiency, and transparency of government services and procedures. By analyzing large amount of data from various repositories that include data concerning demography, traffic, weather, legal affairs, transport, water supply, education, etc., well-informed policy decisions may be made by the government. The paper employs an AI framework to design an effective traffic management system wherein it evaluates and comprehends a complicated traffic forecast by investigating five machine learning (ML) models, including Multilayer Perceptron (MLP), Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), Light Gradient-Boosting Machine (LGBM) Regression, and Random Forest (RF) Regression networks by training and testing a traffic dataset from Kaggle. This framework seeks to significantly take care of traffic congestion at various junction points of a city by analyzing traffic volume at different hours of the day, day of the week, and seasons of the year over a duration of one year and eight months from November 2015 to July 2017. The superiority of the MLP model is demonstrated by multiple data analyses of the traffic dataset, which are followed by simulation and analysis of the prediction model using five ML algorithms. Performance metrics such as root mean square error (RMSE) of 0.235, mean absolute error (MAE) of 0.169, and R2 score of 0.97 are used to demonstrate this. Explainable AI is used to further interpret and explain the outcomes.