Maximizing Success Rate of Payment Routing using Non-stationary Bandits

TL;DR

This paper presents a scalable non-stationary bandit approach for payment routing that improves transaction success rates, validated through simulations and live experiments on a high-volume payment system.

Contribution

It introduces a novel Ray-based architecture for scalable bandit algorithms and demonstrates their effectiveness in real-world payment routing scenarios.

Findings

Achieved a 0.92% increase in transaction success rate over traditional methods.

Successfully scaled the bandit system to handle over 10,000 transactions per second.

Validated the approach through both simulation and live platform experiments.

Abstract

This paper discusses the system architecture design and deployment of non-stationary multi-armed bandit approaches to determine a near-optimal payment routing policy based on the recent history of transactions. We propose a Routing Service architecture using a novel Ray-based implementation for optimally scaling bandit-based payment routing to over 10,000 transactions per second, adhering to the system design requirements and ecosystem constraints with Payment Card Industry Data Security Standard (PCI DSS). We first evaluate the effectiveness of multiple bandit-based payment routing algorithms on a custom simulator to benchmark multiple non-stationary bandit approaches and identify the best hyperparameters. We then conducted live experiments on the payment transaction system on a fantasy sports platform Dream11. In the live experiments, we demonstrated that our non-stationary bandit-based algorithm consistently improves the success rate of transactions by 0.92% compared to the traditional rule-based methods over one month.