In Vitro Fertilization (IVF) is a key assisted reproductive technique designed for individuals facing difficulties in natural conception. Due to IVF's complexity, personalized treatment recommendations are essential to maximize success rates while considering each patient's unique health profile. This study aims to create a machine learning-based, patient-centric Decision Support System (DSS) to optimize IVF treatment. By analyzing extensive patient data, including clinical and lifestyle factors, the study employs advanced algorithms such as Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), Light Gradient Boosting Machine (LightGBM), and Multi-Layer Perceptron (MLP), achieving notable prediction accuracies. Light GBM stands out with an accuracy of 84.97%, precision of 86.95%, and recall of 86.43%, demonstrating its reliability in IVF treatment recommendations. This proposed model not only advances decision-making in IVF treatments but also promotes a personalized, data-driven approach, offering clinicians accurate, consistent insights into each patient’s IVF needs, which can significantly improve treatment outcomes. Future work includes enhancing model robustness across diverse populations.