Missing Data using Decision Forest and Computational Intelligence

TL;DR

This paper presents a method combining autoencoder neural networks, genetic algorithms, and decision forests to estimate and improve handling of missing data under the Missing At Random assumption.

Contribution

It introduces a novel approach integrating neural networks, genetic algorithms, and decision forests for missing data estimation and optimization.

Findings

Decision forests improve estimation accuracy

The combined method reduces mean square error

Effective handling of Missing At Random data

Abstract

Autoencoder neural network is implemented to estimate the missing data. Genetic algorithm is implemented for network optimization and estimating the missing data. Missing data is treated as Missing At Random mechanism by implementing maximum likelihood algorithm. The network performance is determined by calculating the mean square error of the network prediction. The network is further optimized by implementing Decision Forest. The impact of missing data is then investigated and decision forrests are found to improve the results.