Taxi industry is being threatened worldwide by alternative ride share service providers including Uber, Lyft DiDi, Careem and so many other global along with local stakeholders. Nevertheless, taxis remain a substantial service for urban mobility where leading cab companies are exploring data driven BI solutions to facilitate their customers. Along with predicting the taxi demand, it is very important to focus on organizing the fleet so that the taxi drivers can get maximum out of their time on the road. This will also reduce the wait time for the customers and make the taxi ride a delightful experience for them. Predicting taxi demand around a city can help to minimize the lack of balance in some areas where many taxis roam without passengers. In this report, the results from the trained Machine Learning model are presented using publicly available New York City (NYC) taxi data. Analysis was performed for over 2.4 million taxi records to predict the demand for 25 zones over temporal resolution of 24 hours. Range of models including Random Forests, XGboost and Multi Layer Perceptron (MLP) were trained on the data, however 45% of accuracy was achieved from MLP.