Tsukasa Ishigaki | Searcharxiv

arXiv2025

What-If Decision Support for Product Line Extension Using Conditional Deep Generative Models

Product line extension is a strategically important managerial decision that requires anticipating how consumer segments and purchasing contexts may respond to hypothetical product designs that do not yet exist in the market. Such decisions are inherently uncertain because managers must infer future outcomes from historical purchase data without direct market observations. This study addresses this challenge by proposing a data-driven decision support framework that enables forward-looking what-if analysis based on historical transaction data. We introduce a Conditional Tabular Variational Autoencoder (CTVAE) that learns the conditional joint distribution of product attributes and consumer characteristics from large-scale tabular data. By conditioning the generative process on controllable design variables such as container type, volume, flavor, and calorie content, the proposed model generates synthetic consumer attribute distributions for hypothetical line-extended products. This enables systematic exploration of alternative design scenarios without costly market pretests. The framework is evaluated using home-scan panel data covering more than 20,000 consumers and 700 soft drink products. Empirical results show that the CTVAE outperforms existing tabular generative models in capturing conditional consumer attribute distributions. Simulation-based analyses further demonstrate that the generated synthetic data support knowledge-driven reasoning for assessing cannibalization risks and identifying potential target segments. These findings highlight the value of conditional deep generative models as core components of decision support systems for product line extension planning.

cs.LG↗

arXiv2018

Domain-to-Domain Translation Model for Recommender System

Recently multi-domain recommender systems have received much attention from researchers because they can solve cold-start problem as well as support for cross-selling. However, when applying into multi-domain items, although algorithms specifically addressing a single domain have many difficulties in capturing the specific characteristics of each domain, multi-domain algorithms have less opportunity to obtain similar features among domains. Because both similarities and differences exist among domains, multi-domain models must capture both to achieve good performance. Other studies of multi-domain systems merely transfer knowledge from the source domain to the target domain, so the source domain usually comes from external factors such as the search query or social network, which is sometimes impossible to obtain. To handle the two problems, we propose a model that can extract both homogeneous and divergent features among domains and extract data in a domain can support for other domain equally: a so-called Domain-to-Domain Translation Model (D2D-TM). It is based on generative adversarial networks (GANs), Variational Autoencoders (VAEs), and Cycle-Consistency (CC) for weight-sharing. We use the user interaction history of each domain as input and extract latent features through a VAE-GAN-CC network. Experiments underscore the effectiveness of the proposed system over state-of-the-art methods by a large margin.

cs.IR↗