Cervical cancer (CC) arises from abnormal cell proliferation in the cervix, a vital anatomical part of the uterus. It is caused by the human papillomavirus (HPV). CC is the largest cause of mortality among women in underdeveloped nations, emphasizing the critical need for early identification and care. To reduce the burden of CC, it is critical to guarantee early detection and treatment under expert medical supervision. Traditional diagnostic approaches frequently struggle with unbalanced datasets, resulting in poor model performance. This research examines several Artificial Intelligence (AI) models for the identification of CC with a balanced dataset, which is obtained by adopting the Synthetic Minority Over-sampling Technique (SMOTE). In addition to this, we also test the efficacy of Artificial Intelligence (AI) on selected features on the balance dataset. For generalization purposes, we validate our proposed DeepCCi 1.0 model by taking different datasets. We also benchmark our proposed DeepCCi 1.0 model with existing state-of-the-art models. Our proposed DeepCCi 1.0 model overcomes the limitations, especially classification accuracy and computational time, as compared to several traditional approaches. The experimental findings showcase our proposed DeepCCi 1.0 model’s efficacy, with an impressive classification sensitivity, accuracy, F1-score, specificity of 99%, and MCC of 98%. These outcomes highlight the significance of accurate feature selection in improving the efficacy of ML models for CC identification. This research greatly enhances the application of ML and DL techniques and efficient feature engineering in creating more robust and effective tools for identifying CC. As a result, it improves patient outcomes and assists in making therapeutic decisions.