Acetylcholinesterase (AChE) is a crucial enzyme in neurotransmission and a key target in drug discovery, particularly for neurodegenerative diseases such as Alzheimer’s and Parkinson’s. Identifying potent AChE inhibitors requires efficient screening methods due to the high cost and time-consuming nature of experimental approaches. Machine learning (ML) offers a powerful alternative for virtual screening, enabling rapid and accurate bioactivity predictions. In this study, we leveraged the PyCaret framework to develop ML models for predicting AChE inhibitory activity. A dataset of 7,717 compounds and 882 molecular descriptors from the ChEMBL database was used to train classification models, including Light Gradient Boosting Machine (LightGBM), XGBoost, Decision Tree, Extra Trees, and K-Nearest Neighbors (KNN). Performance was evaluated using accuracy, recall, precision, F1-score, and kappa metrics. The results indicate that LightGBM achieved the highest accuracy of 94.30% and an F1-score of 94.29%, followed by XGBoost with 94.02% accuracy and an F1-score of 94.01%, demonstrating their superior predictive capabilities. Additionally, we analyzed computational efficiency, highlighting trade-offs between performance and model complexity. This study establishes ML as a scalable and effective approach for bioactivity prediction, reducing reliance on costly experimental screening. Our findings contribute to AI-driven drug discovery by providing an optimized workflow for identifying potential AChE inhibitors.