Applying the Bayesian Model Using Deep Learning to Analyze 4ABC Technique Risks and its Impact In Performance Quality and Resource Efficiency: an Applied Study in General Company for Power Production

This research objective to grow an integrated model that combines Bayesian inference with deep learning techniques to analyze the danger element associated with the Four-Stage Activity-Based Costing (4ABC) technique and to appraise its influence on performance quality and resource efficiency. The General Company for Electric Power Production - Central Region's operation complexity and reliance on both material and human resources made it the chosen field for the applied study. An applied quantitative methodology was used in conjunction with a descriptive-analytical approach to conduct the research. The company's operational and financial data were prepared and analyzed using artificial intelligence techniques, including deep learning algorithms such as artificial neural networks. In order to account for environmental and operational changes, the probability of risks related to cost allocation and activity loading was estimated and updated using the Bayesian model. The results showed that combining the 4ABC technique with Bayesian modeling and Cost accuracy and resource allocation inefficiencies were significantly improved by deep learning. Through this integration, the operational performance was positively impacted and resource utilization was improved. Furthermore, the predictive framework proved to be an effective means of supporting decision-making for managerial planning, both financially and operationally. In complex production environments, the study suggests adopting this proposed approach and establishing intelligent accounting systems that leverage AI technologies for data analysis and decision-making.