In recent years, the need for Home HealthCare (HHC) has evolved in a context where the population is aging, and chronic diseases are becoming more and more frequent. Home care structures provide care for patients requiring regular and prolonged care outside of the hospital. This includes a wide range of services, from medical care to rehabilitation services, as well as social and psychological support, often provided by health professionals, social workers, and sometimes volunteers. Our research proposes a hybrid solution to optimize HHC Optimization Problem i.e. to optimize resource allocation in the home care field around three main contributions: Classification using support vector machines (SVM) to assign each patient to a type of care and direct them to a specific department, Apply k-means clustering techniques to group patients based on their geographic location and similarity in their types of care and solve the problem of vehicle routing optimization in a home care context using the tabu search metaheuristic by integrating the results of the classification phase to build optimized routes adapted to the individual needs of each patient. We tested our approaches on two categories of instances, The first is generated by integrating two main types of data; geographic data and historical, demographic and medical data of patients. The second category is extracted from the Solomon Benchmark. The results show the effectiveness of our approaches by comparing them with the literature works.