Toward machine learning based prediction services, the prediction server has multiple predictors and selects an appropriate one based on past feedbacks from the clients. In this case, three messages including request, reply, and feedback, are required for each prediction request. Packets are typically transmitted and received via a network protocol stack in OS kernel, and performance improvement can be expected by avoiding the protocol stack since it degrades the communication performance especially for small packets. We implement the prediction server using network optimization approaches including kernel-bypassing and in-NIC processing approaches. Evaluation results show that these network optimizations are beneficial to improve the prediction server performance compared to a baseline prediction server using a standard network protocol stack.