Analysis of Large Scale Complex Networks in the context of Smart Cities

Abstract

Smart real estate investment is one among the smart city perspectives. Identifying the best locations for investment is always a tedious task because of the large number of factors affecting it. Hence, in this work, a novel method is designed that combines data science and network science for location identification (choosing the best condominiums). The city is divided into a cluster of roads/streets and the analysis is carried within a chosen cluster. This research work has four crucial parts- the first is the data science approach which extensively uses statistical modeling and machine learning layers to arrive at the best locations. This method comes with the advantage of having less time complexity but assumes the attributes (features of real estate investors like the number of bedrooms, car parks, and so on) as independent and identically distributed (i.i.d), which is not the case in real estate investment. Hence, this lacuna gave rise to the second part which uses statistical modeling and bipartite network layers