Skip to Main Content
Article navigation
Purpose

To explore the feature importance of e-consumers behaviour and perceived risk in retailing. Also, to classify retail repurchase intentions and risk-taking tendencies using the Random Forest (RF) model.

Design/methodology/approach

Data were collected from 500 retail digital buyers. The classification model was designed using the RF algorithm, which consists of four stages: data acquisition, data analysis and feature selection, model development and random search on parameters. The proposed model was confirmed using key metrics.

Findings

In the theory of planned behaviour interpretive lens, factors such as product features, clarity, product image, feedback, advertisements and product information explain the e-consumers buying intentions. Also, the study classifies the risk features, which are in line with perceived risk theory (explains why certain beliefs influence buying intention under risk). The proposed RF model has an area under curve (AUC) value of 0.97 (repurchase intention) and an AUC value (willingness to take risk) of 0.90, representing excellent discriminative power.

Practical implications

The joint modelling of e-consumers' buying behaviour and perceived risk features offers predictive decision support with enhanced capability to personalise consumer engagement to digital retailers.

Originality/value

Research offers data-driven decisions for segmentation, personalisation and risk-based strategy for retailing, which positively impact e-consumers' decision-making.

Licensed re-use rights only
You do not currently have access to this content.
Don't already have an account? Register

Purchased this content as a guest? Enter your email address to restore access.

Please enter valid email address.
Email address must be 94 characters or fewer.
Pay-Per-View Access
$41.00
Rental

or Create an Account

Close Modal
Close Modal