Identifying SME customers from click feedback on mobile banking apps: Supervised and semi-supervised approaches

Abstract

Nowadays, the banking industry has moved from traditional branch services into mobile banking applications or apps. Using customer segmentation, banks can obtain more insights and better understand their customers' lifestyle and their behavior. In this work, we described a method to classify mobile app user click behavior into two groups, i.e. SME and Non-SME users. This task enabled the bank to identify anonymous users and offer them the right services and products. We extracted hand-crafted features from click log data and evaluated them with the Extreme Gradient Boosting algorithm (XGBoost). We also converted these logs into images, which captured temporal information. These image representations reduced the need for feature engineering, were easier to visualize and trained with a Convolutional Neural Network (CNN). We used ResNet-18 with the image dataset and achieved 71.69% accuracy on average, which outperformed XGBoost, which only achieved 61.70% accuracy. We also evaluated a semi-supervised learning model with our converted image data. Our semi-supervised method achieved 73.12% accuracy, using just half of the labeled images, combined with unlabeled images. Our method showed that these converted images were able to train with a semi-supervised algorithm that performed better than CNN with fewer labeled images. Our work also led to a better understanding of mobile banking user behavior and a novel way of developing a customer segmentation classifier.

Marketing segmentation of banks’ corporate clients based on data mining technique

“…Attempts to develop personalized marketing activities are found in (Tungjitnob et al 2021), but for the first time, we proposed an approach specifically to personalized pricing based on the bank's corporate clients' marketing segments.…”

“…The analysis results can be applied to identify groups of dissatisfied customers, the so-called irritants, and improve their customer experience. Tungjitnob et al (2021) focused on identifying corporate users (business owners) among mobile banking customers. The developed algorithms will allow companies to implement special offers specifically for the corporate segment of online banking users.…”

Formalization of a new stock trend prediction methodology based on the sector price book value for the Colombian market

“…The above is associated with the dynamics concerning market sentiment, which is visualized as the set of combined attitudes that investors may develop towards a specific market ( Tungjitnob et al., 2021 ). In this regard, Kearney and Liu (2014) state that sentiment has little predictive power for future stock market returns in the short term.…”

The Influence of Customer Trust and Value on Customer Loyalty Small and Medium Business (Smes) PT Bank Rakyat Indonesia Branch Office Cilegon

“…The relationship between banks and Small and Medium Business Customers concerns the needs of Small and Medium Business Customers for bank services and the ability and availability of banks to be able to meet the needs of Small and Medium Business Customers (Meslier et al, 2022). The bank's main objective is to create and retain its Small and Medium Enterprises (SMEs) customers (Tungjitnob et al, 2021). With increasing competition in the banking business, every bank must always try to pay attention to the needs and desires of Small and Medium Enterprises (SMEs) customers (Refait-Alexandre & Serve, 2020).…”