Traffic flow, number of vehicles passing a particular point over a given period of time, is an essential indicator for evaluating the performance and condition of road networks, detecting congestion, and predicting traffic trends. Accurate and reliable measurement of traffic flow in urban roads is challenging due to the dynamic nature of intersection signals and comes with high equipment and maintenance cost. WaveTraf™ [1] is a Bluetooth-based Intelligent Traffic System solution widely deployed in the State of Qatar which detects and monitors the movement of Bluetooth-enabled devices anonymously using their unique MAC addresses. Systems such as WaveTraf allow for real-time, low-cost, scalable and non-intrusive traffic flow measurement; however, they could suffer from low detection and sampling rates leading to uncertain and unreliable estimates. In this research, we investigate various machine learning techniques such as Random Forrest, Support Vector Regression Machines and XGBoost for building a generalized model for estimating the actual traffic flow utilizing inexpensive, scalable, and real-time Bluetooth sensors. To increase the accuracy of the estimations, we train and evaluate our algorithms using vehicle count data from expensive cameras. We aim to create a more reliable and cost-effective solution for measuring real-time traffic flow by integrating machine learning techniques.