Rocket Money x Hugging Face: Scaling Volatile ML Models in Production​

"We discovered that they were not just service providers, but partners who were invested in our goals and outcomes” - Nicolas Kuzak, Senior ML Engineer at Rocket Money.

Scaling and Maintaining ML Models in Production Without an MLOps Team

We created Rocket Money (a personal finance app formerly known as Truebill) to help users improve their financial wellbeing. Users link their bank accounts to the app which then classifies and categorizes their transactions, identifying recurring patterns to provide a consolidated, comprehensive view of their personal financial life. A critical stage of transaction processing is detecting known merchants and services, some of which Rocket Money can cancel and negotiate the cost of for members. This detection starts with the transformation of short, often truncated and cryptically formatted transaction strings into classes we can use to enrich our product experience.

The Journey Toward a New System

We first extracted brands and products from transactions using regular expression-based normalizers. These were used in tandem with an increasingly intricate decision table that mapped strings to corresponding brands. This system proved effective for the first four years of the company when classes were tied only to the products we supported for cancellations and negotiations. However, as our user base grew, the subscription economy boomed and the scope of our product increased, we needed to keep up with the rate of new classes while simultaneously tuning regexes and preventing collisions and overlaps. To address this, we explored various traditional machine learning (ML) solutions, including a bag of words model with a model-per-class architecture. This system struggled with maintenance and performance and was mothballed.