Assessment of Bioenergy Prediction and Optimization: Comparative Analysis between Long Short-Term Memory Networks and XGBoost Algorithm

The objective of this research is to enhance the assessment of bioenergy prediction and optimization. The primary data source for the study was the Kaggle dataset. Two distinct groups, Group I and Group 2, each with 20 samples, were employed in this experiment. Group I employed Long Short- Term Memory Networks, whereas Group 2 used XGBoost. The total sample size for the study was forty individuals. Python was used for implementation, and sample size estimates were made for statistical analysis and the ensuing performance comparison. Using clincalc.com, the statistical analysis was performed with alpha (a) set at 0.05, beta (13) at 0.2, and statistical power (G- power) at 85%. The primary goal of the analysis was to compare how well algorithms and long short-term memory networks performed using accuracy value as the primary evaluation criterion. With a two-tailed, p¿0.05 significance value of ¡.001, Long Short Term Memory Networks (97.07%) exceed XGBoost (81.17%) in terms of accuracy. In conclusion, Long Short Term Memory Networks perform more accurately than XGBoost.