Maximum Likelihood Evidence Reasoning-Based Inference with Incomplete Data

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Data mining requires a pre-processing task where the data are prepared, cleaned, integrated, transformed, reduced and discretized to ensure the quality. Incomplete data with missing values is commonly encountered during data cleaning, which might have a major impact on the conclusions that will be drawn from the data. In order to effectively carry out inferential modelling or decision making from incomplete independent variables or explanatory variables and considering different types of uncertainties, this paper adopts a data-driven inference modelling approach, Maximum likelihood evidence reasoning (MAKER) framework, which takes advantage of the incomplete dataset without any imputation that may be required by other conventional machine learning methods. The MAKER framework, therefore, reflects the plausibility of different values of the missing and expresses data-driven support for different values of the missing values.

Bibliographical metadata

Original languageEnglish
Title of host publication25th IEEE International Conference on Automation and Computing
Publication statusAccepted/In press - 21 Jun 2019
Event25th IEEE International Conference on Automation and Computing - Lancaster, United Kingdom
Event duration: 5 Sep 20197 Sep 2019


Conference25th IEEE International Conference on Automation and Computing
Abbreviated titleIEEE ICAC’19
CountryUnited Kingdom
Internet address