Predictive System Based Multi-layered Clustering Model and Least Absolute Shrinkage and Selection Operator (LASSO)

Abstract

Prediction system is one of the tools that can support business decision making. However, existing prediction systems often give high error rate and high computational complexity. In order to make an accurate prediction system while reducing computational complexity, we proposed works that combines multi-layered clustering model using k-means++ as a technique to model data, and feature selection LASSO to predict variables. K-means++ is chosen as clustering method because of its simplicity and its solution through poor initialization, while LASSO is chosen as feature selection because of its good accuracy and its linear nature that cause model complexity to be simpler than non-linear feature selection. First, k-means++ is applied in each layer, then centroids from each layer are transferred into a central processor. Next, a set of centroids is then proceeded using feature selection LASSO to predict variable. Simulation results show that the proposed prediction system has given a good prediction accuracy with MAPE 23.45% and has reduced computational complexity by 89.77%.