Confidential inference (CI) is a technique that utilizes data encryption to maintain privacy and allows inference to be conducted on encrypted data. Several cryptographic mechanisms, including homomorphic encryption, order-preserving encryption (OPE), etc., are applied to CI. In this work, we inspect the validity and efficiency of code-based cryptography for CI in FPGAs for the case of an ensemble of decision trees called the random forest (RF) machine learning (ML) model. FPGAs are an excellent platform for accelerating ML inference because of their low-latency performance, power efficiency, and high reconfigurability. However, creating the hardware description of the encrypted ML model can be difficult, especially for an ML developer unfamiliar with hardware description languages. Thus, we propose an end-to-end methodology that includes high-level synthesis for ease of ML accelerator implementation on FPGAs. We also propose variants of lightweight OPE that meet the criteria for CI in RFs. The successful and efficient implementation has been demonstrated using the Jet and MNIST datasets on the Xilinx Artix-7 FPGA.