Artificial intelligence can change many industries as a global phenomenon. Over the years, this transformation has supported Electronic Markets in reengineering the processes and activities that take place in traditional markets, focusing on improving transaction effectiveness and efficiency. While our dependence on intelligent machines continues to grow, the demand for more transparent and interpretable models equally grows. Thus, explanations for machine decisions and predictions are needed to justify their reliability, which requires greater interpretability and often elaborates the need to understand the algorithms' underlying mechanism. This paper, therefore, proposed models based on Decision Tree (DT), Long Short-Term Memory (LSTM), and an ensemble of the two aforementioned models for improving CLV accuracy, interpretability, and explainability of AI-based models in the multi-category electronic market. An open-source e-commerce Behavior Data from a multi-category store, previously used by similar studies on XAI and CLV, was used in this experiment, ensuring the robustness of the product prediction and explanations and fair comparison. From the results, the models from this study demonstrated remarkable performance in terms of minimal error rates of MAE, MSE, and RMSE, with LSTM outperforming the other models. Regarding explainability and interpretation, the begin_time is ranked as the most relevant feature in CLV prediction.

Designing and validating structural causal model (SCM) correctness from a dataset whose background knowledge is obtained from a research process is not a common phenomenon. Studies have shown that in many critical areas, such as healthcare and education, researchers develop models from direct acyclic graphs (DAG), a component of an SCM, without testing them. This phenomenon is worrisome and is bound to cast a shadow on the inference estimates that may arise from such models. In this study, we have designed a novel application-based SCM for the first time using the background knowledge obtained from the Early Grade Reading Assessment (EGRA) program called the Strengthen Education in Northeast Nigeria (SENSE-EGRA), which is an educational intervention program of the American University of Nigeria (AUN), Yola, on the letter identification subtask. This project was sponsored by the United States Agency for International Development (USAID). We employed the conditional independence test (CIT) criteria for the validation of the SCM’s correctness, and the results show a near-perfect SCM.