Crude oil price prediction using Artificial Neural Network-Backpropagation (ANN-BP) and Particle Swarm Optimization (PSO) methods

Abstract

Crude oil price fluctuations significantly affect commodity market price fluctuations, so a sudden drop in oil prices will cause a slowdown in the economy and other commodities. This is very important for Indonesia, one of the world's oil-producing countries, to gain multiple benefits from oil exports when world oil prices increase and increase economic growth. Therefore, a system is needed to predict world crude oil prices. In this case, the Particle Swarm Optimization (PSO) algorithm is applied as the optimization of the weight parameters in the Artificial Neural Network-Backpropagation (ANN-BP) method. We compared the ANN-BP–PSO and ANN-BP methods to obtain the method with the best causation value based on the MAPE and MSE results. PSO aims to find the best weight value by iterating the process of finding and increasing position, speed, Pbest, and Gbest until the iteration is complete. The results showed that the ANN-BP-PSO process was classified as very good and had a lower predictive error rate than the ANN-BP method based on the MAPE and MSE values, which is 5.02007% and 7.15827% compared to 6.28323% and 13.86345.

Modeling And Enhancing Crude Oil Price Forecasting Using Enhanced Set Algebra-Based Heuristic Algorithm-Based Extreme Learning Machine

“…This novel approach is harnessed for the training of an ELM Artificial Neural Network (ANN). In the interest of comparison, we also train the same ELM model using alternative evolutionary algorithms such as GA (Holland,1975;Latif & Herawati, 2016), PSO (Eberhart and Kennedy, 1995;Purwinarko & Amalia Langgundi, 2023), MBO Chen et al, 2017;Melingi et al, 2022), and the original SAHA algorithm. Consequently, we construct five hybrid models: GA-ELM, PSO-ELM, MBO-ELM, SAHA-ELM, and ESAHA-ELM.…”