This study explores the use of SMILES as a feature for predicting corrosion inhibition efficiency (CIE) for N-heterocyclic compounds, replacing quantum chemical properties (QCP). The gradient boosting regressor (GBR) model outperforms other models like KNN and SVR. SMILES accurately predicts CIE for various datasets, showing potential as a standalone feature. Results indicate a moderate correlation between SMILES representation and corrosion inhibition properties. The proposed method identifies novel N-heterocyclic derivatives with high CIE, suggesting its utility in discovering corrosion inhibitors. Corrosion is a major challenge in various industries, requiring innovative strategies for effective corrosion inhibition. Organic-based corrosion inhibitors are non-toxic, eco-friendly, and cost-effective. However, experimental evaluation is resource-intensive and time-consuming. Machine learning (ML) offers a promising alternative due to its speed, reliability, and cost-effectiveness. In materials informatics, ML is used for designing and discovering new materials, including corrosion inhibitors. QSPR techniques are often used to assess material performance, revealing significant relationships between QCP and CIE. Various studies have shown that ML models like ANN and RF outperform traditional methods in predicting CIE. However, QCP-based models require intensive and time-consuming DFT calculations. To address this, the study proposes using SMILES as a feature for ML predictions. SMILES is a text-based notation representing molecular structure, providing valuable information on topology and substructure. This method expedites computation of molecular properties and chemical interactions, making it suitable for ML studies beyond corrosion inhibition. The study uses a novel dataset of N-heterocyclic compounds, comprising 192 data points from four distinct datasets. The results demonstrate the potential of SMILES-based ML in predicting CIE and accelerating the design of corrosion inhibitors. This approach offers a promising path for efficient and sustainable exploration of anti-corrosion materials.This study explores the use of SMILES as a feature for predicting corrosion inhibition efficiency (CIE) for N-heterocyclic compounds, replacing quantum chemical properties (QCP). The gradient boosting regressor (GBR) model outperforms other models like KNN and SVR. SMILES accurately predicts CIE for various datasets, showing potential as a standalone feature. Results indicate a moderate correlation between SMILES representation and corrosion inhibition properties. The proposed method identifies novel N-heterocyclic derivatives with high CIE, suggesting its utility in discovering corrosion inhibitors. Corrosion is a major challenge in various industries, requiring innovative strategies for effective corrosion inhibition. Organic-based corrosion inhibitors are non-toxic, eco-friendly, and cost-effective. However, experimental evaluation is resource-intensive and time-consuming. Machine learning (ML) offers a promising alternative due to its speed, reliability, and cost-effectiveness. In materials informatics, ML is used for designing and discovering new materials, including corrosion inhibitors. QSPR techniques are often used to assess material performance, revealing significant relationships between QCP and CIE. Various studies have shown that ML models like ANN and RF outperform traditional methods in predicting CIE. However, QCP-based models require intensive and time-consuming DFT calculations. To address this, the study proposes using SMILES as a feature for ML predictions. SMILES is a text-based notation representing molecular structure, providing valuable information on topology and substructure. This method expedites computation of molecular properties and chemical interactions, making it suitable for ML studies beyond corrosion inhibition. The study uses a novel dataset of N-heterocyclic compounds, comprising 192 data points from four distinct datasets. The results demonstrate the potential of SMILES-based ML in predicting CIE and accelerating the design of corrosion inhibitors. This approach offers a promising path for efficient and sustainable exploration of anti-corrosion materials.