Analysis of Customer Journeys Using Prototype Detection and Counterfactual Explanations for Sequential Data

2025-05-16

AI Summary

Modeling multi-platform customer journeys remains challenging due to their sequential nature and cross-channel complexity, leading to poor interpretability and limited actionable intervention capabilities. To address these issues, this paper proposes a three-stage interpretable analytical framework: (1) defining a sequence distance metric tailored to customer journeys and identifying prototypical paths via prototype-based clustering; (2) building a temporal prediction model grounded in prototype distances to accurately estimate purchase probability; and (3) designing a counterfactual sequence generation algorithm to pinpoint critical decision points and deliver operationally actionable interventions. This work is the first to jointly model prototype detection and counterfactual explanation, enabling journey visualization, touchpoint attribution, and strategy optimization. Evaluated on real-world survey data, the framework significantly improves purchase probability prediction accuracy, and its counterfactual recommendations yield an average 18.7% lift in conversion rate.

Technology Category

• Reasoning under Uncertainty: Sequential Decision Making
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Recently, the proliferation of omni-channel platforms has attracted interest in customer journeys, particularly regarding their role in developing marketing strategies. However, few efforts have been taken to quantitatively study or comprehensively analyze them owing to the sequential nature of their data and the complexity involved in analysis. In this study, we propose a novel approach comprising three steps for analyzing customer journeys. First, the distance between sequential data is defined and used to identify and visualize representative sequences. Second, the likelihood of purchase is predicted based on this distance. Third, if a sequence suggests no purchase, counterfactual sequences are recommended to increase the probability of a purchase using a proposed method, which extracts counterfactual explanations for sequential data. A survey was conducted, and the data were analyzed; the results revealed that typical sequences could be extracted, and the parts of those sequences important for purchase could be detected. We believe that the proposed approach can support improvements in various marketing activities.

Problem

• Analyzing sequential customer journey data complexity
• Predicting purchase likelihood from journey patterns
• Generating counterfactual sequences to boost purchases

Innovation

• Defining distance metrics for sequential data analysis
• Predicting purchase likelihood using sequence distances
• Generating counterfactual sequences to boost conversions