Abstract:This paper concerns the challenge to evaluate and predict a district vitality index (VI) over the years. There is no standard method to do it, and it is even more complicated to do it retroactively in the last decades. Although, it is essential to evaluate and learn features of the past to predict a VI in the future. This paper proposes a method to evaluate such a VI, based on a k-mean clustering algorithm. The meta parameters of this unsupervised machine learning technique are optimized by a genetic algorithm method. Based on the resulting clusters and VI, a linear regression is applied to predict the VI of each district of a city. The weights of each feature used in the clustering are calculated using a random forest regressor algorithm. This method can be a powerful insight for urbanists and inspire the redaction of a city plan in the smart city context.