Traffic density is an indicator of congestion and the present study explores the use of data-driven techniques for real time estimation and prediction of traffic density. Data-driven techniques require large database, which can be achieved only with the help of automated sensors. However, the available automated sensors developed for western traffic may not work for heterogeneous and lane-less traffic. Hence, the performance of available automated sensors was evaluated first to identify the best inputs to be used for the chosen application. Using the selected data, implementation was carried out and the results obtained were promising, indicating the possibility of using the proposed methodology for real time traveller information under such traffic conditions.