In this next-generation network (NGN) age, data drives us to a future where innovation meets efficiency. The data-driven decisions fulfil rising traffic demands, minimize cost and lead to smarter network infrastructure. The mobile network operators (MNOs) can reduce their cost per bit by locating the area with the highest traffic density, represented in megabytes (MB) per km2. This study proposes a base station (BS) grouping framework assisted by unsupervised machine learning (ML) to locate the desired area for new deployments known as the highest traffic cluster (HTC). It is studied that the appropriate coverage range of cluster (in kilometers) represented as Epsilon (ϵ) is a significant factor in density-based network clustering to minimize the cost per MB (CPM) and achieve maximum utilization of the network. We propose a novel density-based learning technique assisted by real data to determine the appropriate ϵ and to locate the HTC. We have also studied the correlation of anomalous BSs (ABs) under a network planning and optimization context. The algorithm, density-based network clustering (DNC), determines the ABs, identifies the target area and the tuned value of ϵ by satisfying the MNOs’ requirements of the maximum traffic density MB/km2 and the desired service area in km2. We employ k nearest neighbours (k-NN) as a benchmark to evaluate the tuned value of ϵ alongisde other network performance parameters.