The repository is a comprehensive resource for researchers and practitioners in the field of civil engineering and environmental sustainability. It contains a Python code developed to process and analyze data derived from an extensive experimental study on optimizing cement-zeolite mixtures for sand improvement. The code utilizes advanced machine learning techniques, including a back-propagation neural network (BPNN) for predicting mechanical strength and an adaptive geometry estimation-based multi-objective evolutionary algorithm (AGE-MOEA) for optimization. The repository is linked to a detailed dataset available in the Harvard Dataverse, providing the input and output parameters crucial for understanding the unconfined compressive strength of the treated sand samples. To ensure transparency and foster scientific collaboration, the code is released under the CC BY 4.0 license, encouraging sharing, modification, and use of the dataset, provided appropriate credit is given. This repository not only aids in replicating the study's findings but also serves as a foundation for future research endeavors aiming to enhance the sustainability of construction materials. In the shared code, preprocessing steps are meticulously laid out, including data normalization and splitting into training and testing sets to ensure robustness and reliability of the predictive models. Researchers who wish to delve deeper into the nuances of the data and its analysis will find the code an invaluable tool for navigating and expanding upon the frontiers of sustainable civil engineering solutions.