Unlocking Strategic Insights: A Machine Learning Approach to Business Management Optimization
Ali Jabbar Hussein, Saadaldeen Rashid Ahmed, Mohammad K. Abdul-Hussein, Bourair Al-Atta, Duaa A. Majeed, Abadal-Salam T. Hussain, Jamal Fadhil Tawfeq
Abstract
In the field of corporate management, the optimization of strategies stands as a critical attempt to traverse the intricacies of the current marketplace. Despite developments in technology, gaps continue in successfully employing data-driven techniques for strategic decision-making. Ad-dressing this difficulty, our study intends to fill current research gaps by evaluating the potential of machine learning algorithms for company management optimization. Through the use of LSTM, Random Forest, and K-means clustering algorithms, we evaluate a complete dataset covering sales transactions and client profiles. Notably, our results demonstrate the Random Forest model's remarkable performance, obtaining an accuracy of 0.92 and an F1-score of 0.91, under-scoring its usefulness in predictive analytics. By combining theoretical insights with practical applications, our research helps expand approaches for strategic optimization in real-world corporate situations.