ML-for-Workforce-Analytics-Sales-Forecasting-Segmentation-Sentiment-Analysis

The research targets the implementation of machine learning technology to enhance decision-making processes across Human Resources (HR), Sales, Marketing, and Public Relations (PR) business areas. In this study, the HR model employs Logistic Regression, Random Forest, Support Vector Machines (SVM), LightGBM, KNN, XGBoost, and Naive Bayes algorithms to predict employee turnover while identifying key elements that support employee retention. The Sales model in our study uses ARIMA, SARIMA, XGBoost, and Facebook Prophet for time series forecasting, which helps improve inventory management and forecast sales trends. The research in Marketing uses customer segmentation and clustering algorithms, including K-Means Clustering, Gaussian Mixture Models (GMM), DBSCAN, HDBSCAN, Ensemble Clustering, Graph-Based Louvain Clustering, and preprocessing and representation learning techniques like UMAP, Autoencoders, and Contrastive Learning, to enhance marketing campaign optimization and boost customer engagement. The research in Public Relations (PR) uses NLP together with machine learning algorithms including SVM, Naive Bayes, Logistic Regression, Random Forest, and BiLSTM, to analyze customer review sentiments. The research achieves better business intelligence through its integrated approach which also enhances customer interaction and maximizes business processes by using data-driven insights throughout all departments.