Citation
Lee, Eng Keat and Lee, Yvonne Lean Ee (2025) Economic Inequality Analysis and Machine Learning. The Smart Life Revolution, 1 (34). pp. 101-134. ISSN 9781003509196 Full text not available from this repository.Abstract
This chapter studies income and consumption inequality and explores how Machine Learning can address the limitations of traditional econometric model. Income and consumption inequality, when examined at both individual (micro) and national (macro) levels, reveal gaps in earnings and spending patterns across different social groups. The complex relationships between inequalities and micro or macro indicators are often nonlinear at nature, but traditional econometric models rely on linearity assumptions. Machine learning offers the capability of conducting economic inequality studies in a nonlinear environment and has become a promising method to complement traditional econometric models. Moreover, machine learning has found its way into economics study due to its flexibility in processing different data types. Compared to traditional econometric models which require well-structured data, machine learning can accept raw data such as images. In discussing about policymaking, it is essential to acknowledge that while Machine Learning (ML) made significant progress in analysing inequality, its black box nature poses challenges for direct implementation. Fortunately, the advent of explainable ML models such as SHapley Additive exPlanations (SHAP) provides solutions to this challenge. Some recent inequality studies using Machine Learning will be explored, to highlight their transformative impact on current field.
Item Type: | Article |
---|---|
Subjects: | Q Science > QA Mathematics > QA71-90 Instruments and machines |
Divisions: | Faculty of Management (FOM) |
Depositing User: | Ms Suzilawati Abu Samah |
Date Deposited: | 30 Jun 2025 02:14 |
Last Modified: | 30 Jun 2025 02:14 |
URII: | http://shdl.mmu.edu.my/id/eprint/14141 |
Downloads
Downloads per month over past year
![]() |