The abstract provides a thorough assessment of an elaborate classification framework built for impact-level forecasting with an emphasis on ten separate classes. Precision ratings that vary between 92.79% to 95.07% indicate how accurate the model is at properly recognizing instances for every effect level. Recall rates ranging from 90.91% to 94.37% demonstrate the model's capacity to catch a substantial amount of true positive cases. The F1-Score, which balances precision and recall, regularly falls between 93.38% and 94.43%, indicating an equilibrium of performance through all classes. Support values fluctuate between 1096 to 1175 and provide information into the total quantity of instances every class, allowing for a more nuanced view of the way the model performs across different impact levels. The support proportion, set at 0.10 for each class, guarantees that the dataset has a balanced representation. The total accuracy of 83.9979% demonstrates the model's ability to make accurate predictions spanning all impact levels. Macro Average precision, recall, & F1-Score values of roughly 93.66% indicate the model's uniformity concerning accuracy across all classes. The Weighted Average confirms this, indicating a wellbalanced total performance. At 93.66%, the Micro Average, which provides aggregate metrics across every case, attests to the strategy's uniform accuracy. The presented model for classification performs well in estimating impact levels, providing a good combination of accuracy and recall for all classes. The numerical numbers highlight the model's dependability and adaptability for the task in conjunction, demonstrating its capacity to generalize well and produce accurate predictions for varied impact levels in the current dataset.