Interpretation for Variational Autoencoder Used to Generate Financial Synthetic Tabular Data

• DOI: 10.3390/a16020121
• Publication Date: 2023-02-16T08:32:30Z
• Authors: Jinhong Wu; Konstantinos Plat...; Lucy Liu; Ehsan Amjadian; Yuri Lawryshyn
• Keywords: feature importance; Industrial engineering. Management engineering; QA75.5-76.95; 02 engineering and technology; T55.4-60.8; Electronic computers. Computer science; financial synthetic tabular data; sensitivity-based method; 0202 electrical engineering, electronic engineering, information engineering; variational autoencoder; interpretability; feature interaction

Synthetic data, artificially generated by computer programs, has become more widely used in the financial domain to mitigate privacy concerns. Variational Autoencoder (VAE) is one of the most popular deep-learning models for generating synthetic data. However, VAE is often considered a “black box” due to its opaqueness. Although some studies have been conducted to provide explanatory insights into VAE, research focusing on explaining how the input data could influence VAE to create synthetic data, especially for tabular data, is still lacking. However, in the financial industry, most data are stored in a tabular format. This paper proposes a sensitivity-based method to assess the impact of inputted tabular data on how VAE synthesizes data. This sensitivity-based method can provide both global and local interpretations efficiently and intuitively. To test this method, a simulated dataset and three Kaggle banking tabular datasets were employed. The results confirmed the applicability of this proposed method.