Intelligent Most Popular Location Prediction in Cloud Environment through Facebook Check-ins using Multi-Model Ensembling Approach

Abstract

With the advent of check-in functionality in Facebook, people are able to share more information with the world. Almost every person is using social networking sites nowadays, but the amounts of information they share are appreciated by few. In this research, a new model has been designed for identification of Facebook checkins dataset for predicting most popular places for the user that he/she would like to check-in. Two different machine learning environments, Apache Mahout and R Tool, have been used for predicting most popular places. Each platform has its different classification algorithms. These two machine learning platforms through Ensembling technique have been compared and their analysis has been listed out. In both environments, unique multilevel ensemble model is generated for prediction of Facebook more popular places. In the first module, Facebook check-ins dataset has been used on R tool on a standalone machine, machine learning algorithms have been executed on the given dataset to foresee accuracy for the most famous area. Support Vector Machines model has been chosen as a powerful model since it gives the most astounding accuracy of 77.03% after Conditional Inference Tree model and k-Nearest Neighbors Machine model. Further, these 3 models are ensembled leading to 82.12% accuracy. After that k-fold method is applied, this gives the highest accuracy of 88.18%. In the second module, the Mahout Classification machine learning algorithm has been implemented. For Ensembling technique, the top three models have been chosen; afterward these three models are ensembled to get the highest accuracy. The ensemble model of Facebook check-ins accomplishes 91.66% of accuracy. The experimental outcomes have likewise been assessed utilizing 9768 instances that distinctly support the most extreme accuracy through Ensembling and utilize less execution time in machine learning environment.