BO-RF-NSGA-SHAP: Synthetic Data for Sustainable Automobile Seat Design

A synthetic dataset and Python code implementing the BO-RF-NSGA-SHAP framework for sustainable product design. The repository was created by Xinan Liang and last updated on May 31, 2026. The dataset is 252.9 KB in size and is shared under a CC-BY-4.0 license.

Use Cases

• Training surrogate models for design parameter optimization based on the described Random Forest (RF) integration.
• Conducting multi-objective optimization studies using the described NSGA-II algorithm.
• Performing interpretability analysis on design choices using the described SHAP framework.
• Benchmarking Bayesian Optimization (BO) methods in engineering design contexts.

Strengths

• Includes a complete Python implementation of the described framework alongside the data.
• Released under a permissive CC-BY-4.0 license for open use and modification.
• Framework integrates four distinct methodologies (BO, RF, NSGA-II, SHAP) for a systematic approach.

Limitations

• The dataset is synthetic, not based on real-world measurements, which may limit generalizability.
• Row count and column-level documentation are unknown, requiring manual inspection after download.
• The dataset is very small at 252.9 KB, indicating limited scope.

Provenance

Source

Xinan Liang via figshare

Collection Method

Synthetically generated, likely for framework demonstration and validation.

Freshness

Last updated 2026-05-31 08:53:39