The energy industry has continuously strived to develop technology that maximizes drilling performance to reduce the cost per barrel of crude produced & at the same time, minimize the HSE (health, safety, and environment) risk. Rate of penetration (ROP) optimization is one of the primary factors to improve drilling efficiency and to minimize the operational cost of rigs, drilling operation and drilling tools. Traditional ROP models are empirical based which may be inconsistent in field environments and hence the predictive accuracy of such models are low and subjective. With immense drilling data, operational data, geological data collected over years, the drilling engineering started to shift from first principles modeling to data driven modelling which offers an easier way of extracting value in the data by intelligent algorithms. In this study, Artificial Neural Network (ANN) is developed to predict ROP by making use of the offset vertical wells’ real-time surface parameters while drilling. In the ANN, the input-output mapping is designed with interconnected feed-forward back propagation neural network so that the ROP is efficiently predicted at the drilling bit. Data screening methods and feature engineering methods transform the raw data into a processed data so that the model learns effectively. The developed model is cross validated to generalize over a range of inputs and compared with field measurements. With the help of the developed ANN model, a meta-heuristic algorithm is incorporated to optimize ROP thereby reducing the overall cost per foot of the well. This is achieved by designing Particle Swarm Optimization (PSO) algorithm and allowing the PSO to find the best combination of drilling parameters namely weight on bit (WOB), revolutions per minute (RPM) of the drill bit, and flow in the pumps to maximize the ROP under field constraints. This study combines ANN with PSO to optimize ROP based on real time measurements which has immense potential for operating oil and gas companies to aid in well design or to add as an artificial intelligence component in drilling simulator or autonomous driller. © IJSTR 2019.