English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In todays competitive landscape, businesses grapple with customer retention.Churn prediction models, although beneficial, often lack accuracy due to thereliance on a single data source. The intricate nature of human behavior andhigh dimensional customer data further complicate these efforts. To addressthese concerns, this paper proposes a multimodal fusion learning model foridentifying customer churn risk levels in financial service providers. Ourmultimodal approach integrates customer sentiments financial literacy (FL)level, and financial behavioral data, enabling more accurate and bias-freechurn prediction models. The proposed FL model utilizes a SMOGN COREGsupervised model to gauge customer FL levels from their financial data. Thebaseline churn model applies an ensemble artificial neural network andoversampling techniques to predict churn propensity in high-dimensionalfinancial data. We also incorporate a speech emotion recognition modelemploying a pre-trained CNN-VGG16 to recognize customer emotions based onpitch, energy, and tone. To integrate these diverse features while retainingunique insights, we introduced late and hybrid fusion techniques thatcomplementary boost coordinated multimodal co learning. Robust metrics wereutilized to evaluate the proposed multimodal fusion model and hence theapproach validity, including mean average precision and macro-averaged F1score. Our novel approach demonstrates a marked improvement in churnprediction, 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 hybridfusion learning technique compared with late fusion and baseline models.Furthermore, the analysis demonstrates a positive correlation between negativeemotions, low FL scores, and high-risk customers.

Churn Prediction via Multimodal Fusion Learning:Integrating Customer Financial Literacy, Voice, and Behavioral Data