Machine learning models show promise in discrete choice tasks for policy

A new research paper analyzes the effectiveness of various machine learning models in complex discrete choice tasks, particularly for policy-making and preference elicitation. The study found that semi-parametric and non-parametric models generally outperform traditional parametric models. Performance improvements were observed with increased training data and choice rule determinism, with a case study showing a twinned neural network as the best performer. AI

IMPACT This research could lead to more data-driven and accurate preference elicitation for policy decisions.

RANK_REASON The cluster contains a single academic paper published on arXiv. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• Gaussian process
• generalized additive model
• multinomial logistic regression
• Sheng Lun Christine Cao
• Tainan Airport
• twinned neural network

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →