Understanding and Analysing Causal Relations through Modelling using Causal Machine Learning DOI Open Access

D. Naga Jyothi,

Uma N. Dulhare

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(1)

Published: Feb. 11, 2025

The study of causal inference has gained significant attention in artificial intelligence (AI) and machine learning (ML), particularly areas such as explainability, automated diagnostics, reinforcement learning, transfer learning.. This research applies techniques to analyze student placement data, aiming establish cause-and-effect relationships rather than mere correlations. Using the DoWhy Python library, follows a structured four-step approach—Modeling, Identification, Estimation, Refutation—and introduces novel 3D framework (Data Correlation, Causal Discovery, Domain Knowledge) enhance modeling reliability. discovery algorithms, including Peter Clark (PC), Greedy Equivalence Search (GES), Linear Non-Gaussian Acyclic Model (LiNGAM), are applied construct validate robust model. Results indicate that internships (0.155) academic branch selection (0.148) most influential factors placements, while CGPA (0.042), projects (0.035), employability skills (0.016) have moderate effects, extracurricular activities (0.004) MOOCs courses (0.012) exhibit minimal impact. underscores significance reasoning higher education analytics highlights effectiveness ML real-world decision-making. Future work may explore larger datasets, integrate additional educational variables, extend this approach other disciplines for broader applicability.

Language: Английский

Understanding and Analysing Causal Relations through Modelling using Causal Machine Learning DOI Open Access

D. Naga Jyothi,

Uma N. Dulhare

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(1)

Published: Feb. 11, 2025

The study of causal inference has gained significant attention in artificial intelligence (AI) and machine learning (ML), particularly areas such as explainability, automated diagnostics, reinforcement learning, transfer learning.. This research applies techniques to analyze student placement data, aiming establish cause-and-effect relationships rather than mere correlations. Using the DoWhy Python library, follows a structured four-step approach—Modeling, Identification, Estimation, Refutation—and introduces novel 3D framework (Data Correlation, Causal Discovery, Domain Knowledge) enhance modeling reliability. discovery algorithms, including Peter Clark (PC), Greedy Equivalence Search (GES), Linear Non-Gaussian Acyclic Model (LiNGAM), are applied construct validate robust model. Results indicate that internships (0.155) academic branch selection (0.148) most influential factors placements, while CGPA (0.042), projects (0.035), employability skills (0.016) have moderate effects, extracurricular activities (0.004) MOOCs courses (0.012) exhibit minimal impact. underscores significance reasoning higher education analytics highlights effectiveness ML real-world decision-making. Future work may explore larger datasets, integrate additional educational variables, extend this approach other disciplines for broader applicability.

Language: Английский

Citations

3