Personalised online sales using web usage data mining

Customer experiences in the age of artificial intelligence

Artificial intelligence (AI) is revolutionising the way customers interact with brands. There is a lack of empirical research into AI-enabled customer experiences. Hence, this study aims to analyse how the integration of AI in shopping can lead to an improved AI-enabled customer experience. We propose a theoretical model drawing on the trust-commitment theory and service quality model. An online survey was distributed to customers who have used an AI- enabled service offered by a beauty brand. A total of 434 responses were analysed using partial least squares-structural equation modelling. The findings indicate the significant role of trust and perceived sacrifice as factors mediating the effects of perceived convenience, personalisation and AI-enabled service quality. The findings also reveal the significant effect of relationship commitment on AI-enabled customer experience. This study contributes to the existing literature by revealing the mediating effects of trust and perceived sacrifice and the direct effect of relationship commitment on AI-enabled customer experience. In addition, the study has practical implications for retailers deploying AI in services offered to their customers.

•

Artificial intelligence (AI) is changing customer experiences.

•

The study develops a model drawing on trust-commitment theory and service quality model.

•

Trust and perceived sacrifice play significant mediating role.

•

Relationship commitment has a significant effect on AI-enabled customer experience.

•

Perceived convenience and personalisation play a significant role in AI-enabled experiences.

Risk Factors Analysis and Death Prediction in Some Life-Threatening Ailments Using Chi-Square Case-Based Reasoning (χ2 CBR) Model

A wealth of data are available within the health care system, however, effective analysis tools for exploring the hidden patterns in these datasets are lacking. To alleviate this limitation, this paper proposes a simple but promising hybrid predictive model by suitably combining the Chi-square distance measurement with case-based reasoning technique. The study presents the realization of an automated risk calculator and death prediction in some life-threatening ailments using Chi-square case-based reasoning (χ² CBR) model. The proposed predictive engine is capable of reducing runtime and speeds up execution process through the use of critical χ² distribution value. This work also showcases the development of a novel feature selection method referred to as frequent item based rule (FIBR) method. This FIBR method is used for selecting the best feature for the proposed χ² CBR model at the preprocessing stage of the predictive procedures. The implementation of the proposed risk calculator is achieved through the use of an in-house developed PHP program experimented with XAMP/Apache HTTP server as hosting server. The process of data acquisition and case-based development is implemented using the MySQL application. Performance comparison between our system, the NBY, the ED-KNN, the ANN, the SVM, the Random Forest and the traditional CBR techniques shows that the quality of predictions produced by our system outperformed the baseline methods studied. The result of our experiment shows that the precision rate and predictive quality of our system in most cases are equal to or greater than 70%. Our result also shows that the proposed system executes faster than the baseline methods studied. Therefore, the proposed risk calculator is capable of providing useful, consistent, faster, accurate and efficient risk level prediction to both the patients and the physicians at any time, online and on a real-time basis.

Retail sales prediction and item recommendations using customer demographics at store level

This paper outlines a retail sales prediction and product recommendation system that was implemented for a chain of retail stores. The relative importance of consumer demographic characteristics for accurately modeling the sales of each customer type are derived and implemented in the model. Data consisted of daily sales information for 600 products at the store level, broken out over a set of non-overlapping customer types. A recommender system was built based on a fast online thin Singular Value Decomposition. It is shown that modeling data at a finer level of detail by clustering across customer types and demographics yields improved performance compared to a single aggregate model built for the entire dataset. Details of the system implementation are described and practical issues that arise in such real-world applications are discussed. Preliminary results from test stores over a one-year period indicate that the system resulted in significantly increased sales and improved efficiencies. A brief overview of how the primary methods discussed here were extended to a much larger data set is given to confirm and illustrate the scalability of this approach.