Predicting Small-Scale Industry Growth Under Government Credit Programs: A Data-Driven Machine Learning Approach

DOI

10.2991/978-94-6239-678-4_19How to use a DOI?

Keywords

Government Credit Programs; Small-Scale Industries; SME Growth; Credit Allocation; Firm Performance

Abstract

This paper will explore how government credit programs affect the development of small-scale industries (SSIs) and build a predictive machine-learning model that helps in predicting the performance of firms. The study utilizes empirical strategy that incorporates causal inference and predictive analytics using data of 300 small-scale firms. Propensity Score Matching (PSM) has been used to address the issue of selection bias matching credit-supported firms with similar non-beneficiaries using observed firm attributes. To estimate the causal effects of government credit in the growth of sales, they estimate the Average Treatment Effect on the Treated (ATT). To supplement the causal analysis, various machine-learn algorithms are trained to forecast firm growth in terms of credit amount, firm age, managerial experience, working capital and other performance indicators, namely; Random Forest, Gradient Boosting, Support Vector Regression, and Multiple Linear Regression. RMSE, MAE and R 2 measures are used to imagine model performance. Results indicate that the positive causality effect of government credit on the growth of firms is significant and that firms supported by credit perform better than matched controls. The results of machine learning indicate that Random Forest has the best predictive accuracy and credit amount and working capital are the most influential features. The research findings are that government credit programs significantly increase the SSI performance and AI-based models are useful in policy targeting.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Bikkulal Bhukya
AU  - Gurunadham Goli
AU  - Geetha Manoharan
PY  - 2026
DA  - 2026/05/28
TI  - Predicting Small-Scale Industry Growth Under Government Credit Programs: A Data-Driven Machine Learning Approach
BT  - Proceedings of the 2nd International Conference on Recent Advancement and Modernization in Sustainable Intelligent Technologies & Applications (RAMSITA-2026)
PB  - Atlantis Press
SP  - 232
EP  - 244
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-678-4_19
DO  - 10.2991/978-94-6239-678-4_19
ID  - Bhukya2026
ER  -