An Artificial Intelligence and Machine Learning Framework for Predictive Decision Analytics in Business and Industrial Operations

Abstract

Predictive decision analytics is gaining significance for better planning, resource allocation, and optimization of operations in business & industry. The issue of forecasting electricity prices is a relevant one as the volatility of prices directly affects procurement, production scheduling and operating costs. This study developed an artificial intelligence and machine learning framework for predictive decision analytics using electricity price forecasting as the application domain. A publicly available dataset comprising 23,304 observations and 11 variables was analysed. Historical electricity load, lagged electricity prices, day, and season were used as predictors of the current electricity price. Random Forest, XGBoost, and Gradient Boosting models were developed using an 80:20 train–test split. Model performance was evaluated using MAE, RMSE, MAPE, R², five-fold time-series cross-validation, and SHAP-based interpretation. All three models achieved comparable predictive performance. XGBoost produced the highest R² (0.8870) and lowest RMSE (927.43), while Gradient Boosting achieved the lowest MAE (575.34) and MAPE (10.44%). Time-series cross-validation reported a mean R² of 0.7823, confirming stable predictive capability under changing temporal conditions. SHAP analysis identified recent historical electricity prices, particularly P(T−1) and P(T−24), as the most influential predictors. The results prove that ensemble machine learning is a credible and explainable approach to electricity price prediction, which can be utilized for procurement planning, budgeting, production scheduling, and decision-making for business and industry. .