The Bitcoin Lightning Network is a layer 2 protocol designed to facilitate fast and inexpensive Bitcoin transactions. It operates by establishing channels between users, where Bitcoin is locked and transactions are conducted off-chain until the channels are closed, with only the initial and final transactions recorded on the blockchain. Routing transactions through intermediary nodes is crucial for users without direct channels, allowing these routing nodes to collect fees for their services. Nodes announce their channels to the network, forming a graph with channels as edges. In this paper, we analyze the graph structure of the Lightning Network and investigate the statistical relationships between node properties using machine learning, particularly Graph Neural Networks (GNNs). We formulate a series of tasks to explore these relationships and provide benchmarks for GNN architectures, demonstrating how topological and neighbor information enhances performance. Our evaluation of several models reveals the effectiveness of GNNs in these tasks and highlights the insights gained from their application.

In recent years, with the development of easy to use learning environments, implementing and reproducible benchmarking of reinforcement learning algorithms has been largely accelerated by utilizing these frameworks. In this article, we introduce the Dynamic Fee learning Environment (DyFEn), an open-source real-world financial network model. It can provide a testbed for evaluating different reinforcement learning techniques. To illustrate the promise of DyFEn, we present a challenging problem which is a simultaneous multi-channel dynamic fee setting for off-chain payment channels. This problem is well-known in the Bitcoin Lightning Network and has no effective solutions. Specifically, we report the empirical results of several commonly used deep reinforcement learning methods on this dynamic fee setting task as a baseline for further experiments. To the best of our knowledge, this work proposes the first virtual learning environment based on a simulation of blockchain and distributed ledger technologies, unlike many others which are based on physics simulations or game platforms.

Innoviti Payment Solutions runs a payments platform that has an ability to add intelligence to traditional payment channels, enhancing their value. Merchants, brands and financial service providers use these intelligent payment channels to reduce cost and drive sales of their products. In a media report recently, the company claimed that its machine learning (ML)-based Path Predictor technology has helped enable Google Pay across its stores. The combination of UPI through Google Pay and Path Predictor has led to volumes climbing to nearly 10% for several stores on the Innoviti network.

Online payment providers have been servicing customers all over the world since CyberCash opened its virtual doors in 1995. Unfortunately, the growing number of companies relying on online payment providers has created an epidemic of fraud. According to one recent report, the rate of fraud has increased 45%, to nearly $60 billion in recent years. In Australia alone, online payment fraud has exploded to $476 million. Online payment providers like PayPal have started turning to machine learning, as they strive to tackle the growing number of cybercriminals seeking to exploit their customers.