Age estimation and gender prediction using facial features have become crucial in computer vision and machine learning, with applications in healthcare, security, and social media. This review explores recent advancements, analyzing various methods, datasets, and preprocessing techniques while highlighting their strengths and limitations. It provides a comparative analysis of different models based on accuracy and performance, offering insights into the current challenges and potential directions for future research. A combination of the UTKFace or Adience dataset and a deep CNN-based model with proper preprocessing yields the highest accuracy in age and gender prediction. The study further reveals the future directions in this area like the integration of multimodal data, such as speech and text, can provide richer feature sets that improve prediction accuracy.