Bank transactions embeddings help to uncover current macroeconomics

TL;DR

This paper introduces a neural network-based method to estimate macroeconomic indexes from bank transaction data, providing faster and more accurate insights than traditional autoregressive models, especially during crises.

Contribution

The paper presents an efficient neural network approach with a smart sampling scheme to derive macroeconomic indexes from large-scale transaction data, outperforming baseline methods.

Findings

Neural network approach outperforms baseline on handcrafted features.

Embeddings reveal correlation between transaction activity and macroeconomic indexes.

Method enables fast, accurate macroeconomic index estimation from transaction streams.

Abstract

Macroeconomic indexes are of high importance for banks: many risk-control decisions utilize these indexes. A typical workflow of these indexes evaluation is costly and protracted, with a lag between the actual date and available index being a couple of months. Banks predict such indexes now using autoregressive models to make decisions in a rapidly changing environment. However, autoregressive models fail in complex scenarios related to appearances of crises. We propose to use clients' financial transactions data from a large Russian bank to get such indexes. Financial transactions are long, and a number of clients is huge, so we develop an efficient approach that allows fast and accurate estimation of macroeconomic indexes based on a stream of transactions consisting of millions of transactions. The approach uses a neural networks paradigm and a smart sampling scheme. The results show that our neural network approach outperforms the baseline method on hand-crafted features based on transactions. Calculated embeddings show the correlation between the client's transaction activity and bank macroeconomic indexes over time.