empirical investigation of alternative semi-supervised segmentation methodologies

Abstract

Segmentation of data for the purpose of enhancing predictive modelling is a well-established practice in the banking industry. Unsupervised and supervised approaches are the two main types of segmentation and examples of improved performance of predictive models exist for both approaches. However, both focus on a single aspect – either target separation or independent variable distribution – and combining them may deliver better results. This combination approach is called semi-supervised segmentation. Our objective was to explore four new semi-supervised segmentation techniques that may offer alternative strengths. We applied these techniques to six data sets from different domains, and compared the model performance achieved. The original semi-supervised segmentation technique was the best for two of the data sets (as measured by the improvement in validation set Gini), but others outperformed for the other four data sets. Significance: We propose four newly developed semi-supervised segmentation techniques that can be used as additional tools for segmenting data before fitting a logistic regression. In all comparisons, using semi-supervised segmentation before fitting a logistic regression improved the modelling performance (as measured by the Gini coefficient on the validation data set) compared to using unsegmented logistic regression.

The influence of the practices of big data analytics applications on bank performance: filed study

“…The findings showed a positive and significant relationship between the level of practicing BDA applications and bank performance. Several studies support this finding Zhong et al, 2016;Bremser et al, 2017;Breed and Verster, 2019). For example, Maroufkhani et al (2019) noted that BDA had been considered among the first capabilities that can improve bank performance.…”

“…Influence of the big data analytics adoption/practices on bank performance The literature on issues of business performance of BDA practicing and business value is still fragmented and lacks attempts to integrate the current studies' results Zhong et al, 2016;Bremser et al, 2017;Breed and Verster, 2019) . "Big data analytics is now considered a game-changer that can enable improved business efficiency and effectiveness because of its high operational and strategic potential" (Wamba et al, 2017;Mikalef et al, 2017;Al-Shiakhli, 2019).…”

“…Banks offer personalized product offerings through online banking, mobile banking and ATMs. Efforts to reduce risk in banking transactions and increase access to reach a wider customer base require access to an enormous amount of data and the ability to process this data to draw meaningful conclusions that can be used for decision-making (Zhong et al , 2016; Breed and Verster, 2019; Rana,2019). This is where BDA prepares to play an important role in boosting the growth of the banking industry as well as mitigating the amount of risk.…”