Determinants of Profitability in Non-Financial Sectors: a Panel Data and Machine Learning Analysis of Indonesian Firms from 2012 to 2023
DOI:
https://doi.org/10.59141/jrssem.v5i5.1227Keywords:
Profitability, Return on Assets, Earnings per Share, Panel Data, Machine LearningAbstract
Profitability is a crucial measure of financial stability and operational success for firms. In Indonesia, the capital market has grown significantly, with the Indonesia Stock Exchange (IDX) reaching a market capitalization of IDR 11.67 quadrillion by 2023. However, there remains a gap in studies that comprehensively analyze the determinants of profitability across all non-financial sectors in Indonesia. This research aims to identify and analyze the determinants of profitability in Indonesian non-financial companies using both traditional panel data regression and machine learning techniques. Using quarterly data from 816 non-financial companies listed on the IDX from 2012 to 2023, this study employs panel regression with a fixed effects model and Driscoll-Kraay standard errors. Return on assets (ROA) and earnings per share (EPS) are employed as profitability measures, while firm size (LSIZE), company efficiency (CE), liquidity (LIQ), market power (MP), sales growth (SG), and sustainable growth rate (LSGR) are investigated as explanatory variables. Results from the panel regression analysis reveal that, except for LIQ, all variables have a positive and significant impact on profitability. The analysis is further refined using machine learning techniques, specifically Random Forest, XGBoost, and a deep learning neural network, which conclude that the most important variable influencing ROA is company efficiency, while the most important variable influencing EPS is firm size
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Boedy Christian, Valentino Budhidharma

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike 4.0 International. that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.










