client2vec: Towards Systematic Baselines for Banking Applications
This work addresses productivity challenges for data scientists in banking by automating baseline creation, but it is incremental as it builds on existing autoencoder methods.
The authors tackled the inefficiency in data science workflows by developing client2vec, an internal library that uses marginalized stacked denoising autoencoders on banking transaction data to create client embeddings, resulting in improved productivity for tasks like client segmentation and targeting.
The workflow of data scientists normally involves potentially inefficient processes such as data mining, feature engineering and model selection. Recent research has focused on automating this workflow, partly or in its entirety, to improve productivity. We choose the former approach and in this paper share our experience in designing the client2vec: an internal library to rapidly build baselines for banking applications. Client2vec uses marginalized stacked denoising autoencoders on current account transactions data to create vector embeddings which represent the behaviors of our clients. These representations can then be used in, and optimized against, a variety of tasks such as client segmentation, profiling and targeting. Here we detail how we selected the algorithmic machinery of client2vec and the data it works on and present experimental results on several business cases.