International Journal of Scientific Research and Engineering Development

This research applies a Random Forest machine learning model to real sales data in order to classify customer order statuses. The study aims to evaluate the model’s predictive performance and explore how order status probabilities behave under uncertain conditions using Monte Carlo Simulation. The methodology includes data cleaning, feature encoding, model training, and simulation of random sales scenarios. Results showed a perfect classification performance with 100% accuracy. The simulation further indicated that the “Shipped” status had the highest probability under varying inputs. Overall, the study demonstrates the effectiveness of combining machine learning and simulation techniques for business data analysis.