Dichotomic Pattern Mining with Applications to Intent Prediction from Semi-Structured Clickstream Datasets

TL;DR

This paper presents a pattern mining framework for semi-structured datasets that leverages outcome dichotomy to generate meaningful pattern embeddings, enhancing predictive performance and interpretability in customer intent prediction from clickstream data.

Contribution

The paper introduces a novel dichotomic pattern mining approach that creates interpretable pattern embeddings for semi-structured data, improving downstream predictive tasks.

Findings

Pattern embeddings improve intent prediction accuracy.

Method retains interpretability of patterns.

Framework effectively handles semi-structured clickstream data.

Abstract

We introduce a pattern mining framework that operates on semi-structured datasets and exploits the dichotomy between outcomes. Our approach takes advantage of constraint reasoning to find sequential patterns that occur frequently and exhibit desired properties. This allows the creation of novel pattern embeddings that are useful for knowledge extraction and predictive modeling. Finally, we present an application on customer intent prediction from digital clickstream data. Overall, we show that pattern embeddings play an integrator role between semi-structured data and machine learning models, improve the performance of the downstream task and retain interpretability.