Optimization of Machine Learning Algorithms Through Outlier Data Separation for Predicting Concrete Compressive Strength

Faisal Ananda; Hendra Saputra; Nurul Fahmi; Eko Prayitno; Sinatu Sadiah Shapie; Mohamad Azwan Bin Ikhwat; Mohd Nur Azmi Nordin; Andicha Zain; Fadhillah Binti Mohd. Nasir

doi:10.25299/jgeet.2025.10.02.21896

Authors

Faisal Ananda Department of Civil Engineering, Politeknik Negeri Bengkalis, Jl. Bathin Alam-Sei Alam Bengkalis, Indonesia
Hendra Saputra Department of Civil Engineering, Politeknik Negeri Bengkalis, Jl. Bathin Alam-Sei Alam Bengkalis, Indonesia
Nurul Fahmi Department of Informatics Engineering, Politeknik Negeri Bengkalis, Jl. Bathin Alam-Sei Alam Bengkalis, Indonesia
Eko Prayitno Department of Informatics Engineering, Politeknik Negeri Bengkalis, Jl. Bathin Alam-Sei Alam Bengkalis, Indonesia
Sinatu Sadiah Shapie Department of Civil Engineering, Polytechnic Port Dickson, Jl. Jalan Pantai 71050 Si Rusa Negeri Sembilan, Malaysia.
Mohamad Azwan Bin Ikhwat Department of Civil Engineering, Polytechnic Malacca, Plaza Pandan Malim, 75250 Melaka, Malaysia
Mohd Nur Azmi Nordin Department of Mechanical Engineering, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, 76100 Durian Tunggal, Melaka, Malaysia
Andicha Zain Former Doctoral Candidate in Mechanical Engineering, University of Miskolc, Egyetem út 1, 3515 Miskolc, Hungary
Fadhillah Binti Mohd. Nasir Department of Civil Engineering, Polytechnic Merlimau, Jalan Merlimau-Jasin, 77300 Merlimau, Melaka, Malaysia

DOI:

https://doi.org/10.25299/jgeet.2025.10.02.21896

Keywords:

Predictive Models, Outlier, Evaluations, hyperparameter tuning

Abstract

This study investigates the comparative performance of ten machine learning models—Linear Regression, SVM, Neural Network, Decision Tree, Random Forest, Gradient Boosting, AdaBoost, XGBoost, LightGBM, and CatBoost—in predicting concrete compressive strength. The research emphasizes practical applications in construction, where accurate predictions can improve material design and structural reliability. Through detailed evaluation using MAE, RMSE, and R² metrics, CatBoost and Linear Regression emerged as top-performing models. A rigorous hyperparameter tuning process, employing grid search, significantly enhanced models like SVM and Neural Network, increasing their R² by over 80%. However, tuning occasionally led to reduced performance due to overfitting or unsuitable parameter selection. Outlier analysis using the Z-score method revealed nuanced effects across models: while SVM and Decision Tree benefited from outlier removal, models like Neural Network and CatBoost experienced performance degradation, indicating their reliance on diverse data patterns. These findings underscore the importance of tailored tuning and outlier handling strategies. Future work will incorporate advanced optimization techniques (e.g., Bayesian optimization) and robust cross-validation to further improve model generalization and stability.

Downloads

Download data is not yet available.

References

A Ilemobayo, J., Durodola, O., Alade, O., J Awotunde, O., T Olanrewaju, A., Falana, O., Ogungbire, A., Osinuga, A., Ogunbiyi, D., Ifeanyi, A., E Odezuligbo, I., E Edu, O., 2024. Hyperparameter Tuning in Machine Learning: A Comprehensive Review. J. Eng. Res. Rep. 26, 388–395.

Akmal, F., Dzulizar, M.C.R., Rafli, M.F., Az-Zahra, F., Haq, M.I.K., Dharmawan, I.A., 2023. Machine learning prediction of tortuosity in digital rock. J. Geosci. Eng. Environ. Technol. 8, 06–12.

Alyami, M., Ullah, I., AlAteah, A.H., Alsubeai, A., Alahmari, T.S., Farooq, F., Alabduljabbar, H., 2025. Machine learning models for predicting the compressive strength of cement-based mortar materials: Hyper tuning and optimization. Structures 71, 107931.

Anugerah Simanjuntak, Rosni Lumbantoruan, Kartika Sianipar, Rut Gultom, Mario Simaremare, Samuel Situmeang, Erwin Panggabean, 2024. Research and Analysis of IndoBERT Hyperparameter Tuning in Fake News Detection. J. Nas. Tek. Elektro Dan Teknol. Inf. 13, 60–67.

Anwar, M.K., 2025. A comparative performance analysis of machine learning models for compressive strength prediction in fly ash-based geopolymers concrete using reference data. Case Stud. Constr. Mater.

Asteris, P.G., Skentou, A.D., Bardhan, A., Samui, P., Pilakoutas, K., 2021. Predicting concrete compressive strength using hybrid ensembling of surrogate machine learning models. Cem. Concr. Res. 145, 106449.

Ayiah-Mensah, F., Bosson-Amedenu, S., Baah, E.M., Addor, J.A., 2025. Advancements in seasonal rainfall forecasting: A seasonal auto-regressive integrated moving average model with outlier adjustments for Ghana’s Western Region. Sci. Afr. 28, e02632.

Chodha, A., 2024. Cement Slump SVR.

Choi, J.-H., Kim, D., Ko, M.-S., Lee, D.-E., Wi, K., Lee, H.-S., 2023. Compressive strength prediction of ternary-blended concrete using deep neural network with tuned hyperparameters. J. Build. Eng. 75, 107004.

Dash, P.K., 2023. Influence of chemical constituents of binder and activator in predicting compressive strength of fly ash-based geopolymer concrete using firefly-optimized hybrid ensemble machine learning model. Mater. Today Commun.

Dong, Y., 2025. A new method to evaluate features importance in machine-learning based prediction of concrete compressive strength. J. Build. Eng.

El Hachimi, C., Belaqziz, S., Khabba, S., Daccache, A., Ait Hssaine, B., Karjoun, H., Ouassanouan, Y., Sebbar, B., Kharrou, M.H., Er-Raki, S., Chehbouni, A., 2025. Physics-informed neural networks for enhanced reference evapotranspiration estimation in Morocco: Balancing semi-physical models and deep learning. Chemosphere 374, 144238.

Fan, C., Ding, Y., Zheng, Y., 2025. Bond strength and failure mode prediction model for recycled aggregate concrete based on intelligent algorithm optimized support vector machine. Structures 71, 107999.

Ghafoorian Heidari, S.I., Safehian, M., Moodi, F., Shadroo, S., 2024. Predictive modeling of the long-term effects of combined chemical admixtures on concrete compressive strength using machine learning algorithms. Case Stud. Chem. Environ. Eng. 10, 101008.

Gokcesu, K., Neyshabouri, M.M., Gökcesu, H., Kozat, S.S., 2019. Sequential Outlier Detection Based on Incremental Decision Trees. IEEE Trans. SIGNAL Process. 67.

Guzmán-Torres, J.A., Domínguez-Mota, F.J., Alonso-Guzmán, E.M., Tinoco-Guerrero, G., Martínez-Molina, W., 2024. ConcreteXAI: A multivariate dataset for concrete strength prediction via deep-learning-based methods. Data Brief 53, 110218.

Harmiyati, Al Ihsyan, N., Syahputri, D., 2024. Analysis of the Effect of Bagasse Addition on Compressive Strength, Porosity, and Permeability of Pervious Concrete as Material for Green Building Program. J. Geosci. Eng. Environ. Technol. 9, 420–425.

Hassan, B.R., Hamid, F.L., Karim, H., Hussein, A.B., Abdulrahman, P.H., Mohammed, L.M., Hatim, L.A., Mahmood, S.S., 2024. Predicting shear strength of fiber-reinforced concrete beams reinforced with longitudinal FRP bars with machine learning techniques. Aust. J. Struct. Eng. 1–16.

Huang, P., Dai, K., Yu, X., 2023. Machine learning approach for investigating compressive strength of self-compacting concrete containing supplementary cementitious materials and recycled aggregate. J. Build. Eng. 79, 107904.

Jiang, Y., Wang, Y., Zhang, J., Xie, B., Liao, J., Liao, W., 2021. Outlier detection and robust variable selection via the penalized weighted LAD-LASSO method. J. Appl. Stat. 48, 234–246.

Khan, M.I., 2023. Intelligent data-driven compressive strength prediction and optimization of reactive powder concrete using multiple ensemble-based machine learning approach. Constr. Build. Mater.

Kumar, N., Martin, H., Raubal, M., 2024. Enhancing Deep Learning-Based City-Wide Traffic Prediction Pipelines Through Complexity Analysis. Data Sci. Transp. 6, 24.

Kumar, R., Althaqafi, E., Patro, S.G.K., Simic, V., Babbar, A., Pamucar, D., Singh, S.K., Verma, A., 2024. Machine and deep learning methods for concrete strength Prediction: A bibliometric and content analysis review of research trends and future directions. Appl. Soft Comput. 164, 111956.

Li, Z., Pei, T., Ying, W., Srubar, W.V., Zhang, R., Yoon, J., Ye, H., Dabo, I., Radlińska, A., 2024. Can domain knowledge benefit machine learning for concrete property prediction? J. Am. Ceram. Soc. 107, 1582–1602.

Liang, K., Zhao, J., Zhang, Z., Guan, W., Pan, M., Li, M., 2024. Data-driven AI algorithms for construction machinery. Autom. Constr. 167, 105648.

Liu, L., Xie, C., Hu, W., Li, Y., 2024. Recursive Elimination of “Outliers” to Get Benchmark Dataset. IEEE Access 12, 98319–98325.

Liu, Y., Yu, H., Guan, T., Chen, P., Ren, B., Guo, Z., 2025. Intelligent prediction of compressive strength of concrete based on CNN-BiLSTM-MA. Case Stud. Constr. Mater. 22, e04486.

Luo, X., Li, Y., Wang, Q., Mu, J., Liu, Y., 2024. Machine learning based modeling for predicting the compressive strength of solid waste material-incorporated Magnesium Phosphate Cement. J. Clean. Prod. 442, 141172.

Lv, Z., Chen, C., Tan, Z., Hu, B., Jin, J., 2025. Establishment of strength evolution model and life prediction for diatomite-modified concrete under freeze-thaw conditions. Constr. Build. Mater. 463, 140049.

Mahmood, M.S., Elahi, A., Zaid, O., Alashker, Y., Șerbănoiu, A.A., Grădinaru, C.M., Ullah, K., Ali, T., 2023. Enhancing compressive strength prediction in self-compacting concrete using machine learning and deep learning techniques with incorporation of rice husk ash and marble powder. Case Stud. Constr. Mater. 19, e02557.

Marchiori, R., Song, S., Moon, J., 2025. Developing heat stress training assessments: A training-driven methodology approach to enhance safety in the construction industry. J. Safety Res. 92, 262–271.

Miyan, N., Krishnan, N.M.A., Das, S., 2024. Integrating data imputation and augmentation with interpretable machine learning for efficient strength prediction of fly ash-based alkali-activated concretes. J. Build. Eng. 98, 111248.

Moutassem, F., Chidiac, S.E., 2016. Assessment of concrete compressive strength prediction models. KSCE J. Civ. Eng. 20, 343–358.

Nurcahya, A., Alexandra, A., Zainuddin, S.Z., Az-Zahra, F., Haq, M.I.K., Dharmawan, I.A., 2023. Machine Learning Application of Two-Dimensional Fracture Properties Estimation. J. Geosci. Eng. Environ. Technol. 8, 01–05.

Parmo, P., Wardhana, I., 2024. Investigating the Influence of Cement and Additive Normalization on Concrete Compressive Strength: A Statistical Analysis. Comput. Eng. Phys. Model. 7.

Rusman, J., Haryati, B.Z., Michael, A., 2023. Optimisasi Hiperparameter Tuning pada Metode Support Vector Machine untuk Klasifikasi Tingkat Kematangan Buah Kopi. J. Komput. Dan Inform. 11, 195–202.

Sathiparan, N., 2025. Predicting compressive strength in cement mortar: The impact of fly ash composition through machine learning. Sustain. Chem. Pharm. 43, 101915.

Tak, M.S.N., Feng, Y., Mahgoub, M., 2025. Advanced Machine Learning Techniques for Predicting Concrete Compressive Strength.

Talpur, S.A., Thansirichaisree, P., Anotaipaiboon, W., Mohamad, H., Zhou, M., Ejaz, A., Hussain, Q., Saingam, P., Chaimahawan, P., 2025. Data-driven prediction of failure loads in low-cost FRP-confined reinforced concrete beams. Compos. Part C Open Access 17, 100579.

Touati, S., Boumediri, H., Karmi, Y., Chitour, M., Boumediri, K., Zemmouri, A., Moussa, A., Fernandes, F., 2025. Performance analysis of steel W18CR4V grinding using RSM, DNN-GA, KNN, LM, DT, SVM models, and optimization via desirability function and MOGWO. Heliyon 11, e42640.

Vargas, J.F., Oviedo, A.I., Ortega, N.A., Orozco, E., Gómez, A., Londoño, J.M., 2024. Machine-Learning-Based Predictive Models for Compressive Strength, Flexural Strength, and Slump of Concrete. Appl. Sci. 14, 4426.

Wang, C., Li, C., Feng, Y., Wang, S., 2025. Predicting hydropower generation: A comparative analysis of Machine learning models and optimization algorithms for enhanced forecasting accuracy and operational efficiency. Ain Shams Eng. J. 16, 103299.

Yu, J., Chang, X., Hu, S., Yin, H., Wu, J., 2024. Combining travel behavior in metro passenger flow prediction: A smart explainable Stacking-Catboost algorithm. Inf. Process. Manag. 61, 103733.