Article
Computer Science, Artificial Intelligence
Bing Zhu, Cheng Qian, Seppe vanden Broucke, Jin Xiao, Yuanyuan Li
Summary: Churn prediction on imbalanced data is challenging. This paper proposes a new bagging-based selective ensemble paradigm for profit-oriented churn prediction in class imbalance scenarios. Experimental results show that the proposed method outperforms state-of-the-art ensemble solutions in both accuracy-based and profit-based measures.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Nhi N. Y. Vo, Shaowu Liu, Xitong Li, Guandong Xu
Summary: Customer retention is crucial in the financial services industry, and machine learning has been used to predict client churn risks. While existing approaches mainly rely on structured data, mining unstructured data can provide more insights. The research introduced a model utilizing spoken contents in phone communication for customer churn prediction, which showed promising results in accurately predicting risks and generating meaningful insights.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Chemistry, Multidisciplinary
Fatima Enehezei Usman-Hamza, Abdullateef Oluwagbemiga Balogun, Luiz Fernando Capretz, Hammed Adeleye Mojeed, Saipunidzam Mahamad, Shakirat Aderonke Salihu, Abimbola Ganiyat Akintola, Shuib Basri, Ramoni Tirimisiyu Amosa, Nasiru Kehinde Salahdeen
Summary: Customer churn is a critical issue in the telecommunications industry. Researchers have developed intelligent decision forest models to predict churn, which outperformed existing methods. These models efficiently distinguish churn customers from non-churn ones.
APPLIED SCIENCES-BASEL
(2022)
Article
Management
Sebastian Maldonado, Gonzalo Dominguez, Diego Olaya, Wouter Verbeke
Summary: This study introduces a profit-based classification approach for churn prediction in the mutual fund industry, redefining the maximum profit measure to address varying customer lifetime values. Empirical testing demonstrates the method's superiority in maximizing profit, offering an important contribution to decision-making in business analytics.
OMEGA-INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE
(2021)
Article
Green & Sustainable Science & Technology
Lewlisa Saha, Hrudaya Kumar Tripathy, Tarek Gaber, Hatem El-Gohary, El-Sayed M. El-kenawy
Summary: Predicting churn rate is crucial for the success and profitability of the telecommunication industry. This study compares different learning strategies to build a churn prediction model, aiming to accurately predict customer churn without compromising profit. The evaluation results show that CNN and ANN techniques perform better than other methods, achieving high accuracy rates on both datasets.
Article
Computer Science, Artificial Intelligence
Ping Jiang, Zhenkun Liu, Lifang Zhang, Jianzhou Wang
Summary: Customer churn prediction is widely used to detect potential churners, stimulating customer retention and reducing churn loss. A hybrid profit-driven churn prediction model is proposed that considers both return and cost. Synthetic minority over-sampling technique-nominal continuous is used to predict churners and non-churners, and feature selection based on a modified multi-objective atomic orbital search and extreme learning machine is used to obtain suitable variables for churn prediction with maximum return and minimum cost. Experimental results on real-life datasets show that the proposed model achieves high-quality forecasting performance with higher profit, providing reliable references for operators and decision-makers.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Operations Research & Management Science
Bram Janssens, Matthias Bogaert, Astrid Bague, Dirk Van den Poel
Summary: This paper aims to enhance the current practices in business-to-business (B2B) customer churn prediction modelling by introducing a novel expected maximum profit measure and a gradient boosting classifier called B2Boost. By considering customer value and company profit, this study improves the current practices and shows significant expected maximal profit gains.
ANNALS OF OPERATIONS RESEARCH
(2022)
Article
Computer Science, Artificial Intelligence
Adnan Amin, Awais Adnan, Sajid Anwar
Summary: Customer churn is a complex challenge for competitive organizations, and this study proposes an adaptive learning approach using the Naive Bayes classifier with a Genetic Algorithm to improve churn prediction. The proposed approach outperforms baseline classifiers and enhances prediction performance on publicly available datasets.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Misuk Kim
Summary: Real-time processing and analysis of data are crucial in financial markets due to their direct impact on profits. This study introduces a novel data mining framework focusing on interpretability, prediction metrics, and reporting methods, which was applied to financial prediction problems with successful results.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Irina V. Pustokhina, Denis A. Pustokhin, R. H. Aswathy, T. Jayasankar, C. Jeyalakshmi, Vicente Garcia Diaz, K. Shankar
Summary: This research develops a dynamic Customer Churn Prediction (CCP) strategy using text analytics with metaheuristic optimization, chaotic pigeon inspired optimization based feature selection, and long short-term memory with stacked auto encoder model. Further improvement in CCP performance is achieved through sunflower optimization hyperparameter tuning. Simulation analysis demonstrates superior performance with maximum accuracy on the applied datasets.
INFORMATION PROCESSING & MANAGEMENT
(2021)
Article
Computer Science, Interdisciplinary Applications
Jiabing Xu, Jiarui Liu, Tianen Yao, Yang Li
Summary: This study aims to transform existing telecom operators from traditional Internet operators to digital-driven services and improve the overall competitiveness of telecom enterprises. It applies data mining to telecom user classification and processes existing telecom user data through data integration, cleaning, standardization, and transformation. The research establishes a telecom customer churn prediction model using the backpropagation neural network (BPNN) algorithm and deploys the MapReduce programming framework on the Hadoop platform. The accuracy of the model is improved by 25.36%, and the running time is shortened by about twice, compared to existing research.
Article
Computer Science, Artificial Intelligence
Mai Kiguchi, Waddah Saeed, Imran Medi
Summary: Educational Technology (EdTech) is an industry that combines education and technological advancements. Digital game-based learning (DGBL) is a specific category within EdTech. This study proposes an approach for defining and predicting churn in DGBL by analyzing a dataset from a Japanese company. The results indicate the effectiveness of the approach in determining and predicting churn in DGBL.
APPLIED SOFT COMPUTING
(2022)
Article
Mathematics
Matthias Bogaert, Lex Delaere
Summary: In the study, a large scale benchmark analysis was conducted to evaluate the performance of various classifiers in predicting customer churn. The results showed that heterogeneous ensembles consistently outperformed homogeneous ensembles and single classifiers. The study also identified specific configurations of heterogeneous ensembles that ranked highest in terms of different performance metrics. This research contributes to the literature by providing a comprehensive benchmark study in customer churn prediction.
Article
Computer Science, Information Systems
Zhen Wei, Li Zhang, Lei Zhao
Summary: In this study, a new oversampling method called MPP-SMOTE is proposed to address the issue of imbalanced learning. The method removes noisy samples and divides the minority samples into two types based on their probability of belonging to the minority class. It then separately selects and generates synthetic samples for each type based on different sample-generation schemes. Experimental results demonstrate that MPP-SMOTE outperforms other oversampling methods in terms of imbalanced-learning metrics for common classifiers.
INFORMATION SCIENCES
(2023)
Article
Social Sciences, Interdisciplinary
Denisa Melian, Andreea Dumitrache, Stelian Stancu, Alexandra Nastu
Summary: This paper examines customer churn behavior in the telecommunications industry and tests the effectiveness and performance of commonly used data mining techniques. By determining predictive models and key indicators, early warning signals of customer churn can be detected, and measures can be taken to increase customer retention.
POSTMODERN OPENINGS
(2022)
Article
Management
George Petrides, Darie Moldovan, Lize Coenen, Tias Guns, Wouter Verbeke
Summary: This study evaluates the effectiveness of cost-sensitive learning methods in improving the profitability of credit scorecards. The results show that these methods can increase profitability, especially for channels with higher default rates.
JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY
(2022)
Article
Management
Lize Coenen, Wouter Verbeke, Tias Guns
Summary: This study investigates the use of machine learning for a finer-grained risk estimation task in spot factoring. The results show that regression models can lead to higher profits and better risk distribution in spot factoring.
JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY
(2022)
Article
Computer Science, Artificial Intelligence
Jakob Raymaekers, Wouter Verbeke, Tim Verdonck
Summary: This paper proposes a formalized, data-driven method for increasing classification precision while maintaining model interpretability and reducing the risk of overfitting. By exploring the discretization of continuous variables through spline functions, the method captures nonlinear effects in predictor variables and yields interpretable predictors with a small number of discrete values. Furthermore, the extension of the weight-of-evidence approach with shrinkage estimators improves the ability to utilize both nonlinear and categorical predictors effectively.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
George Petrides, Wouter Verbeke
Summary: The study introduces a unified framework for cost-sensitive ensemble methods, categorizing and comparing them, including extensions and generalizations for methods like AdaBoost, Bagging, and Random Forest.
DATA MINING AND KNOWLEDGE DISCOVERY
(2022)
Article
Management
Sebastiaan Hoppner, Bart Baesens, Wouter Verbeke, Tim Verdonck
Summary: Credit card transaction fraud is a global issue, and financial institutions are increasingly relying on data-driven methods to develop fraud detection systems for detecting and preventing fraudulent transactions. The article introduces two novel classifiers that minimize the instance-dependent cost measure when learning a classification model, highlighting the potential to reduce fraud losses.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2022)
Article
Computer Science, Information Systems
Toon Vanderschueren, Tim Verdonck, Bart Baesens, Wouter Verbeke
Summary: Predictive models are increasingly used to optimize decision-making and minimize costs. This work compared the predict-then-optimize approach with the predict-and-optimize approach in cost-sensitive classification. The key finding was that the decision-making strategy was generally more effective than training with a task-specific loss or their combination.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Felix Vandervorst, Wouter Verbeke, Tim Verdonck
Summary: This paper proposes a novel approach to evaluate the risk of underwriting premium fraud by using conditional density estimates. The approach supports insurance companies in identifying fraudulent applications and can adapt to changes in pricing policy. It can also detect outliers and predict underwriting fraud.
DECISION SUPPORT SYSTEMS
(2022)
Article
Management
Wouter Verbeke, Diego Olaya, Marie-Anne Guerry, Jente Van Belle
Summary: Individual treatment effect models optimize decision-making by predicting the effect of treatment on specific outcomes of individual instances. This article introduces a cost-sensitive causal classification approach based on predictions of individual treatment effects, which allows selecting instances to treat and maximize expected causal profit.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2023)
Article
Computer Science, Artificial Intelligence
Sam Verboven, Muhammad Hafeez Chaudhary, Jeroen Berrevoets, Vincent Ginis, Wouter Verbeke
Summary: Multitask learning can enhance the performance of a task by sharing representations with related auxiliary tasks. However, static loss weights often lead to poor results. This paper introduces an intelligent weighting algorithm called HydaLearn that addresses the shortcomings of static loss weights by connecting the main-task gain to individual task gradients, allowing for dynamic loss weighting at the minibatch level. Experiments show significant performance improvements on synthetic and real-world datasets.
APPLIED INTELLIGENCE
(2023)
Article
Economics
Jente Van Belle, Ruben Crevits, Wouter Verbeke
Summary: In this paper, the authors define forecast (in)stability as the variability in forecasts caused by updating them over time. They propose an extension to the N-BEATS deep learning architecture for time series forecasting, optimizing forecasts for both accuracy and stability. Experimental results show that the proposed extension improves both accuracy and stability compared to the original N-BEATS architecture, suggesting that including forecast instability in the loss function can serve as a regularization mechanism.
INTERNATIONAL JOURNAL OF FORECASTING
(2023)
Article
Computer Science, Artificial Intelligence
Floris Devriendt, Jente Van Belle, Tias Guns, Wouter Verbeke
Summary: This article investigates the application of learning to rank techniques in causal classification and its combination with uplift modeling. A unified formalization model is proposed, and a new performance metric is introduced. The effectiveness of this method is demonstrated through experiments, but the results are only applicable in specific scenarios.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Engineering, Industrial
Toon Vanderschueren, Robert Boute, Tim Verdonck, Bart Baesens, Wouter Verbeke
Summary: This study uses causal inference to learn the effect of preventive maintenance frequency on asset overhaul and failure rates, based on observational data. The learned outcomes are used to optimize maintenance schedules and minimize the combined cost of failures, overhauls, and preventive maintenance.
INTERNATIONAL JOURNAL OF PRODUCTION ECONOMICS
(2023)
Article
Statistics & Probability
Simon De Vos, Toon Vanderschueren, Tim Verdonck, Wouter Verbeke
Summary: In this paper, the authors demonstrate that instance-dependent cost-sensitive (IDCS) learning methods are sensitive to noise and outliers in relation to instance-dependent misclassification costs. They propose a three-step framework to enhance the robustness of IDCS methods by automatically detecting outliers, correcting outlying cost information, and constructing an IDCS learning method. The newly proposed r-cslogit method, tested on synthetic and semi-synthetic data, shows superior savings compared to its non-robust counterpart for different levels of noise and outliers.
ADVANCES IN DATA ANALYSIS AND CLASSIFICATION
(2023)
Article
Computer Science, Artificial Intelligence
Christopher Bockel-Rickermann, Tim Verdonck, Wouter Verbeke
Summary: The literature on fraud analytics and detection has experienced a significant increase in the past decade, resulting in a wide range of research topics and a lack of overall organization. This paper provides an overview of fraud analytics, analyzes published records, identifies prominent domains, challenges, performance metrics, and methods, and proposes a framework and keywording strategy for future research. Additionally, the paper addresses the challenge of accessing public datasets and offers requirements for suitable data sets, while providing an online database for fellow researchers to explore and build upon.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Mathematics, Interdisciplinary Applications
Jeroen Berrevoets, Sam Verboven, Wouter Verbeke
Summary: Applying causal methods in fields like healthcare, marketing, and economics is gaining increasing interest. The research on individual-treatment-effect optimization, also known as uplift modelling, has reached its peak in precision medicine and targeted advertising. Existing techniques have shown their utility in many scenarios, but they suffer from limitations in dynamic environments. To address this, the researchers propose a novel optimization target called uplifted contextual multi-armed bandit, which effectively improves upon the state-of-the-art according to experiments on real and simulated data.
JOURNAL OF CAUSAL INFERENCE
(2022)
Review
Management
Vinicius N. Motta, Miguel F. Anjos, Michel Gendreau
Summary: This survey presents a review of optimization approaches for the integration of demand response in power systems planning and highlights important future research directions.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2024)
Article
Management
Philipp Schulze, Armin Scholl, Rico Walter
Summary: This paper proposes an improved branch-and-bound algorithm, R-SALSA, for solving the simple assembly line balancing problem, which performs well in balancing workloads and providing initial solutions.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2024)
Article
Management
Roshan Mahes, Michel Mandjes, Marko Boon, Peter Taylor
Summary: This paper discusses appointment scheduling and presents a phase-type-based approach to handle variations in service times. Numerical experiments with dynamic scheduling demonstrate the benefits of rescheduling.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2024)
Article
Management
Oleg S. Pianykh, Sebastian Perez, Chengzhao Richard Zhang
Summary: Efficient scheduling is crucial for optimizing resource allocation and system performance. This study focuses on critical utilization and efficient scheduling in discrete scheduling systems, and compares the results with classical queueing theory.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2024)
Review
Management
Hamed Jahani, Babak Abbasi, Jiuh-Biing Sheu, Walid Klibi
Summary: Supply chain network design is a large and growing area of research. This study comprehensively surveys and analyzes articles published from 2008 to 2021 to detect and report financial perspectives in SCND models. The study also identifies research gaps and offers future research directions.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2024)
Article
Management
Patrick Healy, Nicolas Jozefowiez, Pierre Laroche, Franc Marchetti, Sebastien Martin, Zsuzsanna Roka
Summary: The Connected Max-k-Cut Problem is an extension of the well-known Max-Cut Problem, where the objective is to partition a graph into k connected subgraphs by maximizing the cost of inter-partition edges. The researchers propose a new integer linear program and a branch-and-cut algorithm for this problem, and also use graph isomorphism to structure the instances and facilitate their resolution. Extensive computational experiments show that, if k > 2, their approach outperforms existing algorithms in terms of quality.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2024)
Article
Management
Victor J. Espana, Juan Aparicio, Xavier Barber, Miriam Esteve
Summary: This paper introduces a new methodology based on the machine learning technique MARS for estimating production functions that satisfy classical production theory axioms. The new approach overcomes the overfitting problem of DEA through generalized cross-validation and demonstrates better performance in reducing mean squared error and bias compared to DEA and C2NLS methods.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2024)
Article
Management
Stefano Nasini, Rabia Nessah
Summary: In this paper, the authors investigate the impact of time flexibility in job scheduling, showing that it can significantly affect operators' ability to solve the problem efficiently. They propose a new methodology based on convex quadratic programming approaches that allows for optimal solutions in large-scale instances.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2024)
Article
Management
Zhiqiang Liao, Sheng Dai, Timo Kuosmanen
Summary: Nonparametric regression subject to convexity or concavity constraints is gaining popularity in various fields. The conventional convex regression method often suffers from overfitting and outliers. This paper proposes the convex support vector regression method to address these issues and demonstrates its advantages in prediction accuracy and robustness through numerical experiments.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2024)
Article
Management
Kuo-Hao Chang, Ying-Zheng Wu, Wen-Ray Su, Lee-Yaw Lin
Summary: The damage and destruction caused by earthquakes necessitates the evacuation of affected populations. Simulation models, such as the Stochastic Pedestrian Cell Transmission Model (SPCTM), can be utilized to enhance disaster and evacuation management. The analysis of SPCTM provides insights for government officials to formulate effective evacuation strategies.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2024)
Article
Management
Qinghua Wu, Mu He, Jin-Kao Hao, Yongliang Lu
Summary: This paper studies a variant of the orienteering problem known as the clustered orienteering problem. In this problem, customers are grouped into clusters and a profit is associated with each cluster, collected only when all customers in the cluster are served. The proposed evolutionary algorithm, incorporating a backbone-based crossover operator and a destroy-and-repair mutation operator, outperforms existing algorithms on benchmark instances and sets new records on some instances. It also demonstrates scalability on large instances and has shown superiority over three state-of-the-art COP algorithms. The algorithm is also successfully applied to a dynamic version of the COP considering stochastic travel time.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2024)
Article
Management
Bjorn Bokelmann, Stefan Lessmann
Summary: Estimating treatment effects is an important task for data analysts, and uplift models provide support for efficient allocation of treatments. However, evaluating uplift models is challenging due to variance issues. This paper theoretically analyzes the variance of uplift evaluation metrics, proposes variance reduction methods based on statistical adjustment, and demonstrates their benefits on simulated and real-world data.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2024)
Article
Management
Congzheng Liu, Wenqi Zhu
Summary: This paper proposes a feature-based non-parametric approach to minimizing the conditional value-at-risk in the newsvendor problem. The method is able to handle both linear and nonlinear profits without prior knowledge of the demand distribution. Results from numerical and real-life experiments demonstrate the robustness and effectiveness of the approach.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2024)
Article
Management
Laszlo Csato
Summary: This paper compares the performance of the eigenvalue method and the row geometric mean as two weighting procedures. Through numerical experiments, it is found that the priorities derived from the two eigenvectors in the eigenvalue method do not always agree, while the row geometric mean serves as a compromise between them.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2024)
Article
Management
Guowei Dou, Tsan-Ming Choi
Summary: This study investigates the impact of channel relationships between manufacturers on government policies and explores the effectiveness of positive incentives versus taxes in increasing social welfare. The findings suggest that competition may be more effective in improving sustainability and social welfare. Additionally, government incentives for green technology may not necessarily enhance sustainability.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2024)