Data Analysis for the Management of Delinquent Portfolios in Virtual Contact Centers
Article Sidebar
Main Article Content
Introduction: virtual contact centers providing BPO services have experienced exponential growth in the customer service, sales, and collections sectors in recent years. This expansion has driven a continuous search for greater operational efficiency and effectiveness in user management, especially in the context of portfolio recovery and optimizing management task times.
Objective: the objective of this study is to analyze historical data using exploratory data analysis and machine learning models to identify strategies that improve operational effectiveness, specifically in terms of the number of portfolios recovered and the time required to complete management tasks.
Methodology: the methodology follows the data lifecycle framework for machine learning projects, covering six stages: from data acquisition to model implementation. Exploratory analysis was applied to understand patterns in the data, and machine learning models were implemented to predict and improve portfolio management performance.
Results: the results were compared with the rule-based model currently used by the company and a manual management approach based on the analysts’ experience. The results demonstrate a 21.8% improvement in effectiveness compared to manual management and a 519.51% improvement over the existing rule-based model.
Conclusions: the study shows that the implementation of machine learning models can significantly enhance operational efficiency in virtual contact centers, greatly surpassing traditional rule-based approaches and manual management. These results highlight the potential of artificial intelligence to transform user management in the BPO services industry, improving both portfolio recovery and task execution times.
- Machine Learning
- Virtual Contact Center
- Debt Recovery
- Punished Portfolio
L. Wang, N. Huang, Y. Hong, L. Liu, X. Guo, and G. Chen, “Voice-based AI in call center customer service: A natural field experiment,” Production and Operations Management, vol. 32, no. 4, pp. 1002-1018, 2023. https://doi.org/10.1111/poms.13953 DOI: https://doi.org/10.1111/poms.13953
B. Li and L. Liu, “Does voice-based AI improve call center operational performance? Event study in a working telecommunication company,” in PACIS 2021 Proceedings, vol. 132, 2021. Available: https://aisel.aisnet.org/pacis2021/132.
F. Kreuter and G. Müller, “A note on improving process efficiency in panel surveys with paradata,” Field Methods, vol. 27, no. 1, pp. 55-65, 2015. https://doi.org/10.1177/1525822X14538205 DOI: https://doi.org/10.1177/1525822X14538205
Z. Zhang, B. Li, and L. Liu, “The impact of AI-based conversational agent on the firms’ operational performance: Empirical evidence from a call center,” Applied Artificial Intelligence, vol. 37, no. 1, 2022. https://doi.org/10.1080/08839514.2022.2157592 DOI: https://doi.org/10.1080/08839514.2022.2157592
Ş. Ozan, “Classification of audio segments in call center recordings using convolutional recurrent neural networks,” arXiv e-prints, Art. no. arXiv:2106.02422, 2021. Available: https://arxiv.org/pdf/2106.02422
C. Sánchez, S. Maldonado, and C. Vairetti, “Improving debt collection via contact center information: A predictive analytics framework,” Decision Support Systems, vol. 159, p. 113812, 2022. https://doi.org/10.1016/j.dss.2022.113812 DOI: https://doi.org/10.1016/j.dss.2022.113812
M. Pinelis and D. Ruppert, “Machine learning portfolio allocation,” The Journal of Finance and Data Science, vol. 8, pp. 35-54, 2022. https://doi.org/10.1016/j.jfds.2021.12.001 DOI: https://doi.org/10.1016/j.jfds.2021.12.001
K. Sivamayilvelan, et al., “Flexible recommendation for optimizing the debt collection process based on customer risk using deep reinforcement learning,” Expert Systems with Applications, vol. 256, p. 124951, 2024. https://doi.org/10.1016/j.jfds.2021.12.001 DOI: https://doi.org/10.1016/j.eswa.2024.124951
G. Lemaitre, F. Nogueira, and C. K. Aridas, “Imbalanced-learn: A Python toolbox to tackle the curse of imbalanced datasets in machine learning,” Journal of Machine Learning Research, vol. 18, pp. 1-5, 2017. Available: https://inria.hal.science/hal-01516244v1.
L. Breiman, “Random forests,” Machine Learning, vol. 45, pp. 5-32, 2001. https://doi.org/10.1023/A:1010933404324 DOI: https://doi.org/10.1023/A:1010933404324
D. A. Pisner and D. M. Schnyer, “Support vector machine,” in Machine Learning, Academic Press, 2020, pp. 101-121. https://doi.org/10.1016/B978-0-12-815739-8.00006-7 DOI: https://doi.org/10.1016/B978-0-12-815739-8.00006-7
T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ‘16), New York, NY, USA: Association for Computing Machinery, 2016, pp. 785-794. https://doi.org/10.1145/2939672.2939785 DOI: https://doi.org/10.1145/2939672.2939785
Á. F. Pinheiro, D. S. da Silveira, and F. B. de Lima Neto, “Use of machine learning for active public debt collection with recommendation for the method of collection via protest,” in CS & IT Conference Proceedings, vol. 12, no. 9, May 2022. https://doi.org/10.5121/csit.2022.120909 DOI: https://doi.org/10.5121/csit.2022.120909
E. Dumitrescu, et al., “Machine learning for credit scoring: Improving logistic regression with non-linear decision-tree effects,” European Journal of Operational Research, vol. 297, no. 3, pp. 1178-1192, 2022. https://doi.org/10.1016/j.ejor.2021.06.053 DOI: https://doi.org/10.1016/j.ejor.2021.06.053
M. Doumpos, et al., “Operational research and artificial intelligence methods in banking,” European Journal of Operational Research, vol. 306, no. 1, pp. 1-16, 2023. https://doi.org/10.1016/j.ejor.2022.04.027 DOI: https://doi.org/10.1016/j.ejor.2022.04.027
S. Akter, et al., “Algorithmic bias in machine learning-based marketing models,” Journal of Business Research, vol. 144, pp. 201-216, 2022. https://doi.org/10.1016/j.jbusres.2022.01.083 DOI: https://doi.org/10.1016/j.jbusres.2022.01.083
A. M. Benavides, et al., Modelo para la predicción de interacciones recibidas en un centro de atención telefónico, Tesis de maestría, Facultad de Ingeniería, Pontificia Universidad Javeriana, Bogotá, Colombia, 2022. [Online]. Available: http://hdl.handle.net/10554/61764
M. Calero, M. Baldeon Calisto, S. Bonilla, and D. Riofrio, “Application of machine learning algorithms for the prediction of payment by agreement in a debt collection company with the CRISP-DM methodology,” in 3rd South American International Conference on Industrial Engineering and Operations Management, May 2022. https://doi.org/10.46254/SA03.20220112 DOI: https://doi.org/10.46254/SA03.20220112
D. M. Arango Correa, L. J. Colmenares Colmenares, and I. C. Rave Contreras, “Comparación entre el método tradicional y algunos basados en inteligencia artificial para el estudio del riesgo crediticio en instituciones financieras colombianas,” 2018. Available: http://hdl.handle.net/10784/12983
S. Tyagi, “Analyzing machine learning models for credit scoring with explainable AI and optimizing investment decisions,” arXiv preprint, arXiv:2209.09362, 2022. Available: https://arxiv.org/abs/2209.09362
Kaggle, “Give Me Some Credit - Kaggle Competition,” Kaggle, Available: https://www.kaggle.com/competitions/GiveMeSomeCredit [Accessed: Feb. 19, 2025].
Downloads
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors grant the journal and Universidad del Valle the economic rights over accepted manuscripts, but may make any reuse they deem appropriate for professional, educational, academic or scientific reasons, in accordance with the terms of the license granted by the journal to all its articles.
Articles will be published under the Creative Commons 4.0 BY-NC-SA licence (Attribution-NonCommercial-ShareAlike).