Kiva.org is an online crowdfunding platform to extend financial services to poor and financially excluded people around the world.For the locations in which Kiva has active loans,our objective is to pair Kiva's data with additional data sources to estimate the welfare level of borrowers in specific regions,based on shared economic and demographic characteristics.
In this Mathematica project we are going to explore the different visualization techniques that can be used to find the some of the meaningful visual graphics from the given dataset.
There are multiple dataset files provided by Kiva of which few of the data is unsupervised/unlabeled for which we are using machine learning methods to find the labels for unlabeled data.
Comparison study has been made on various methods of machine learning models such as Neural Networks, Support Vector Machines, Logistic Regression, Nearest Neighbour and Random Forest to identify best classifier methods and Neural Networks, Gaussian Process , Logistic Regression, Nearest Neighbour and Random Forest to identify best prediction methods for the given dataset.
Data Preprocessing such as replacing the missing values, removal of duplicate values, Data Integration and Data Transformation have been performed on the dataset.