Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Deciphering Customer Satisfaction: A Machine Learning-Oriented Method Using Agglomerative Clustering for Predictive Modeling and Feature Selection

Rezki Nisrine, Mansouri Mohamed, Oucheikh Rachid

Management Systems in Production Engineering

2025

nr 1 (33)

60--70

In contemporary enterprises, customer satisfaction analysis has become a critical area of concentration. Being able to understand and predict customer satisfaction is becoming more and more important as companies try to develop and launch new products. Leveraging customer data intelligently and employing robust data analytics techniques are essential for meeting this imperative. With this objective in mind, the study proposes a machine learning-based approach to analyze and discern the variables influencing customer satisfaction. Specifically, the study utilizes agglomerative clustering for data segmentation and feature identification, followed by a Random Forest Classifier as machine learning (ML) model for prediction. Performance metrics such as accuracy, recall, precision and F1-score are employed for model evaluation, ensuring robustness and reliability in the predictive process. Furthermore, it aims to predict the impact of enhancing specific product attributes on customer satisfaction. To provide a tangible demonstration of the proposed methodology, a comprehensive case study is conducted. By systematically integrating clustering techniques into the feature selection and modeling process, this framework furnishes a structured methodology for data-driven decision-making and predictive analytics. This holistic approach not only enriches the comprehension of intricate datasets but also facilitates the development of resilient predictive models characterized by enhanced accuracy and interpretability. By segmenting customers based on their responses, we discerned specific areas of satisfaction and dissatisfaction, providing actionable insights for targeted strategies aimed at improving overall satisfaction. The insights and customer clustering derived from this study can guide these targeted strategies to enhance customer satisfaction and inform future product development initiatives.

Machine learning for proactive supply chain risk management: predicting delays and enhancing operational efficiency

Rezki Nisrine, Mansouri Mohamed

Management Systems in Production Engineering

2024

nr 3 (32)

345--356

Supply chain (SC) efficacy and efficiency can be severely hampered by supplier delays in orders, especially in the fast-paced business environment of today. Effective risk reduction necessitates the identification of suppliers who are prone to delays and the precise prediction of future interruption. Accurately predicting availability dates is therefore a key factor in successfully executing logistics operations. By leveraging machine learning (ML) techniques, organizations can proactively identify high-risk suppliers, anticipate delays, and implement proactive measures to minimize their impact on manufacturing processes and overall SC performance. This study explores and utilizes various regression and classification ML algorithms to predict future delayed delivery, determine the status of order deliveries, and classify suppliers according to their delivery performance. The employed models include K-Nearest Neighbors (KNN) Random Forest (RF) Classifier and Regression, Gradient Boosting (GB) Regression and Classifier, Linear Regression (LR), Decision Trees(DT) Classifier and Regression, Logistic Regression and Support Vector Machine (SVM) Based on real data, our experiments and evaluation metrics including Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) demonstrate that the ensemble based regression algorithms (RF Regression and GB Regression) provide the best generalization error and outperforms all other regression models tested. Similarly, Logistic regression and GB Classifier outperforms other classification algorithms according to precision, recall, and F1-score metrics. The knowledge obtained from this study could aid in the proactive identification of high-risk suppliers and the application of proactive actions to increase resilience in the face of unanticipated disruptions, in addition to increasing SC efficiency and decreasing manufacturing disturbances.