BeschreibungThe digital economy evolves with a growing amount of sequential marketing data including online browsing histories, location-based trajectories or sequential consumption patterns reflected in music or video streams. Marketing analysts aim at utilizing this kind of data to derive behavioral-based segments and for subsequent targeting of users. However, detecting similarities and measuring distances between sequences pose a number of challenging problems. In particular, in the case of excessively high-dimensional data (i.e., if the numbers of alternatives are high) and increasingly long sequences, traditional similarity-based approaches to time series clustering or sequence alignment algorithms have their known weaknesses and limitations. We present a generic solution to the problem of quantifying similarities in a high-dimensional, dynamic feature space based on a deep neural network approach. Our proposed framework combines recurrent neural network architectures, which are well established in the field of natural language processing, with a specific type of error propagation procedure used in image recognition. Every sequence (e.g., of customer actions) applied on the trained model is translated into a high dimensional vector, which summarizes significant properties (e.g., order, context, embedding, appearance) and serves for deriving distances between sequences. Based on the resulting vector space representations, any standard clustering technique can be applied to segment customers. We demonstrate the newly developed method using internet browsing behavior data and validate the classification performance by matching randomly drawn sequences to the correct original user. Furthermore, we illustrate that the proposed framework allows to track the evolution of customers through the clustered vector space.
|Zeitraum||20 Juni 2019 → 22 Juni 2019|
|Ereignistitel||2019 INFORMS Marketing Science Conference|
Dokumente & Verweise