Missing Data: A Comparison of Neural Network and Expectation Maximisation Techniques

TL;DR

This paper compares neural network and Expectation Maximisation techniques for estimating missing data in real-time applications, highlighting their relative effectiveness across multiple datasets.

Contribution

It provides a comparative analysis of neural network-based and EM-based methods for missing data imputation, which is novel in the context of real-time processing.

Findings

Neural network approach performs comparably to EM in certain datasets.

EM technique shows robustness in handling missing data.

Neural networks offer faster computation in some scenarios.

Abstract

The estimation of missing input vector elements in real time processing applications requires a system that possesses the knowledge of certain characteristics such as correlations between variables, which are inherent in the input space. Computational intelligence techniques and maximum likelihood techniques do possess such characteristics and as a result are important for imputation of missing data. This paper compares two approaches to the problem of missing data estimation. The first technique is based on the current state of the art approach to this problem, that being the use of Maximum Likelihood (ML) and Expectation Maximisation (EM. The second approach is the use of a system based on auto-associative neural networks and the Genetic Algorithm as discussed by Adbella and Marwala3. The estimation ability of both of these techniques is compared, based on three datasets and conclusions are made.