Random Search Hyperparameter Optimization for BPNN to Forecasting Cattle Population

Abstract

Backpropagation Neural Network (BPNN) is a suitable method for predicting the future. It has weaknesses, namely poor convergence speed and instability, requiring parameter tuning to overcome speed problems, and having a high bias. This research uses the Random Search hyperparameter technique to optimize BPNN to automatically select the number of hidden layers, learning rate, and momentum. The added accuracy of momentum will speed up the training process, produce predictions with better accuracy, and determine the best architectural model from a series of faster training processes with low bias. This research will predict the local Indonesian cattle population, which is widely developed by people in the eastern part, especially Madura, in 4 types of cattle: sono cattle, karapan cattle, mixed cattle, and breeder cattle. The results of BPNN hyperparameter measurements with the best model show that hyperparameter optimization did not experience overfitting and experienced an increase in accuracy of 2.5% compared to the Neural Network model without hyperparameter optimization. Based on the test results, the BPNN algorithm parameters with a data ratio of 70:30, the best architecture for backpropagation momentum is 6-6-1, with a learning rate of 0.002, momentum 0.3, which has an MSE during testing of 0.1176 on Karapan type Madurese cattle. Tests based on computing time measurements show that the BPNN hyperparameter algorithm stops at 490 iterations compared to regular BPNN. The research results show that the hidden layers, learning rate, and momentum if optimized simultaneously, have a significant influence in preventing overfitting, increasing accuracy, and having better execution times than without optimization.