IDEAS home Printed from https://ideas.repec.org/p/hal/journl/hal-04320145.html
   My bibliography  Save this paper

Churn Prediction via Multimodal Fusion Learning: Integrating Customer Financial Literacy, Voice, and Behavioral Data
[Prédiction du churn par apprentissage fusionné multimodal : intégration de la littératie financière, des données vocales et comportementales des clients]

Author

Listed:
  • David Hason Rudd

    (UTS - University of Technology Sydney)

  • Huan Huo

    (UTS - University of Technology Sydney)

  • Md. Rafiqul Islam

    (UTS - University of Technology Sydney)

  • Guandong Xu

    (UTS - University of Technology Sydney)

Abstract

In today's competitive landscape, businesses grapple with customer retention. Churn prediction models, although beneficial, often lack accuracy due to the reliance on a single data source. The intricate nature of human behavior and highdimensional customer data further complicate these efforts. To address these concerns, this paper proposes a multimodal fusion learning model for identifying customer churn risk levels in financial service providers. Our multimodal approach integrates customer sentiments, financial literacy (FL) level, and financial behavioral data, enabling more accurate and bias-free churn prediction models. The proposed FL model utilizes a SMOGN-COREG supervised model to gauge customer FL levels from their financial data. The baseline churn model applies an ensemble artificial neural network and oversampling techniques to predict churn propensity in high-dimensional financial data. We also incorporate a speech emotion recognition model employing a pretrained CNN-VGG16 to recognize customer emotions based on pitch, energy, and tone. To integrate these diverse features while retaining unique insights, we introduced late and hybrid fusion techniques that complementary boost coordinated multimodal colearning. Robust metrics were utilized to evaluate the proposed multimodal fusion model and hence the approach's validity, including mean average precision and macro-averaged F1 score. Our novel approach demonstrates a marked improvement in churn prediction, achieving a test accuracy of 91.2%, a Mean Average Precision (MAP) score of 66, and a Macro-Averaged F1 score of 54 through the proposed hybrid fusion learning technique compared with late fusion and baseline models. Furthermore, the analysis demonstrates a positive correlation between negative emotions, low FL scores, and high-risk customers.

Suggested Citation

  • David Hason Rudd & Huan Huo & Md. Rafiqul Islam & Guandong Xu, 2023. "Churn Prediction via Multimodal Fusion Learning: Integrating Customer Financial Literacy, Voice, and Behavioral Data [Prédiction du churn par apprentissage fusionné multimodal : intégration de la l," Post-Print hal-04320145, HAL.
  • Handle: RePEc:hal:journl:hal-04320145
    Note: View the original document on HAL open archive server: https://hal.science/hal-04320145
    as

    Download full text from publisher

    File URL: https://hal.science/hal-04320145/document
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Oechssler, Jörg & Roider, Andreas & Schmitz, Patrick W., 2009. "Cognitive abilities and behavioral biases," Journal of Economic Behavior & Organization, Elsevier, vol. 72(1), pages 147-152, October.
    2. Aurélie Lemmens & Sunil Gupta, 2020. "Managing Churn to Maximize Profits," Marketing Science, INFORMS, vol. 39(5), pages 956-973, September.
    3. De Caigny, Arno & Coussement, Kristof & De Bock, Koen W. & Lessmann, Stefan, 2020. "Incorporating textual information in customer churn prediction models based on a convolutional neural network," International Journal of Forecasting, Elsevier, vol. 36(4), pages 1563-1578.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Chou, Ping & Chuang, Howard Hao-Chun & Chou, Yen-Chun & Liang, Ting-Peng, 2022. "Predictive analytics for customer repurchase: Interdisciplinary integration of buy till you die modeling and machine learning," European Journal of Operational Research, Elsevier, vol. 296(2), pages 635-651.
    2. Benjamin Enke & Florian Zimmermann, 2019. "Correlation Neglect in Belief Formation," The Review of Economic Studies, Review of Economic Studies Ltd, vol. 86(1), pages 313-332.
    3. Abedin, Mohammad Zoynul & Hajek, Petr & Sharif, Taimur & Satu, Md. Shahriare & Khan, Md. Imran, 2023. "Modelling bank customer behaviour using feature engineering and classification techniques," Research in International Business and Finance, Elsevier, vol. 65(C).
    4. Dohmen, Thomas & Falk, Armin & Huffman, David & Marklein, Felix & Sunde, Uwe, 2009. "Biased probability judgment: Evidence of incidence and relationship to economic outcomes from a representative sample," Journal of Economic Behavior & Organization, Elsevier, vol. 72(3), pages 903-915, December.
    5. Corgnet, Brice & DeSantis, Mark & Porter, David, 2020. "The distribution of information and the price efficiency of markets," Journal of Economic Dynamics and Control, Elsevier, vol. 110(C).
    6. Maria Bigoni & Davide Dragone, 2011. "An experiment on experimental instructions," Jena Economics Research Papers 2011-049, Friedrich-Schiller-University Jena.
    7. Lex Borghans & Bas ter Weel, 2008. "Understanding the Technology of Computer Technology Diffusion: Explaining Computer Adoption Patterns and Implications for the Wage Structure," Journal of Income Distribution, Ad libros publications inc., vol. 17(3-4), pages 37-70, September.
    8. Bokelmann, Björn & Lessmann, Stefan, 2024. "Improving uplift model evaluation on randomized controlled trial data," European Journal of Operational Research, Elsevier, vol. 313(2), pages 691-707.
    9. Michalis Drouvelis & Julian C. Jamison, 2015. "Selecting public goods institutions: Who likes to punish and reward?," Southern Economic Journal, John Wiley & Sons, vol. 82(2), pages 501-534, October.
    10. Neyse, Levent & Bosworth, Steven & Ring, Patrick & Schmidt, Ulrich, 2016. "Overconfidence, Incentives and Digit Ratio," Open Access Publications from Kiel Institute for the World Economy 130145, Kiel Institute for the World Economy (IfW Kiel).
    11. Louis Geiler & Séverine Affeldt & Mohamed Nadif, 2022. "A survey on machine learning methods for churn prediction," Post-Print hal-03824873, HAL.
    12. Jonathan Chapman & Erik Snowberg & Stephanie Wang & Colin Camerer, 2018. "Loss Attitudes in the U.S. Population: Evidence from Dynamically Optimized Sequential Experimentation (DOSE)," NBER Working Papers 25072, National Bureau of Economic Research, Inc.
    13. Christopher Gerling & Stefan Lessmann, 2023. "Multimodal Document Analytics for Banking Process Automation," Papers 2307.11845, arXiv.org, revised Nov 2023.
    14. Eizo Akiyama & Nobuyuki Hanaki & Ryuichiro Ishikawa, 2017. "It is Not Just Confusion! Strategic Uncertainty in An Experimental Asset Market," Economic Journal, Royal Economic Society, vol. 127(605), pages 563-580, October.
    15. Antoni Bosch-Domènech & Pablo Brañas-Garza & Antonio M. Espín, 2013. "Can exposure to prenatal sex hormones (2D:4D) predict cognitive reflection?," Working Papers 698, Barcelona School of Economics.
    16. Holden, Stein T. & Tilahun, Mesfin, 2019. "How related are risk preferences and time preferences?," CLTS Working Papers 4/19, Norwegian University of Life Sciences, Centre for Land Tenure Studies, revised 16 Oct 2019.
    17. Ray Saadaoui Mallek & Mohamed Albaity, 2019. "Individual differences and cognitive reflection across gender and nationality the case of the United Arab Emirates," Cogent Economics & Finance, Taylor & Francis Journals, vol. 7(1), pages 1567965-156, January.
    18. repec:cup:judgdm:v:14:y:2019:i:3:p:234-279 is not listed on IDEAS
    19. Kai Duttle & Keigo Inukai, 2015. "Complexity Aversion: Influences of Cognitive Abilities, Culture and System of Thought," Economics Bulletin, AccessEcon, vol. 35(2), pages 846-855.
    20. repec:cup:judgdm:v:15:y:2020:i:5:p:660-684 is not listed on IDEAS
    21. Mohammad Noori, 2016. "Cognitive reflection as a predictor of susceptibility to behavioral anomalies," Judgment and Decision Making, Society for Judgment and Decision Making, vol. 11(1), pages 114-120, January.
    22. Dertwinkel-Kalt, Markus & Riener, Gerhard, 2016. "A first test of focusing theory," DICE Discussion Papers 214, Heinrich Heine University Düsseldorf, Düsseldorf Institute for Competition Economics (DICE).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:hal:journl:hal-04320145. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: CCSD (email available below). General contact details of provider: https://hal.archives-ouvertes.fr/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.