Comparative Study of Machine Learning Classification Models

Ticks of the family Ixodidae are significant public health threats, transmitting pathogens such as the bacteria causing Lyme disease and viruses leading to hemorrhagic fever. Traditional identification methods based on morphology are time-consuming and unreliable during early developmental stages. This study investigates whether supervised machine learning models, using the COI mitochondrial gene as a molecular marker, can accurately classify medically important tick genera (Ixodes, Haemaphysalis, Rhipicephalus, and Amblyomma) to support early detection and vector management strategies. Using supervised machine leanring, 3 modles will be compared: Random Forest, Support Vector Machines and Gradient Boosting Machine all through R. The scripts and final report is available!