Transaction Categorization with Relational Deep Learning in QuickBooks

2025/06/10 by Kaiwen Dong, Dong, Kaiwen, Padmaja Jonnalagedda +13
Computer Science · Decision Sciences · #Computational Engineering #Data Quality and Management #FOS: Computer and information sciences #Finance #Recommender Systems and Techniques #Text and Document Classification Technologies #and Science (cs.CE)

paper · pdf · doi:10.48550/arxiv.2506.09234

openalex publication_date 2025/06/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Automatic transaction categorization is crucial for enhancing the customer experience in QuickBooks by providing accurate accounting and bookkeeping. The distinct challenges in this domain stem from the unique formatting of transaction descriptions, the wide variety of transaction categories, and the vast scale of the data involved. Furthermore, organizing transaction data in a relational database creates difficulties in developing a unified model that covers the entire database. In this work, we develop a novel graph-based model, named Rel-Cat, which is built directly over the relational database. We introduce a new formulation of transaction categorization as a link prediction task within this graph structure. By integrating techniques from natural language processing and graph machine learning, our model not only outperforms the existing production model in QuickBooks but also scales effectively to a growing customer base with a simpler, more effective architecture without compromising on accuracy. This design also helps tackle a key challenge of the cold start problem by adapting to minimal data.

Citations

• Pure Message Passing Can Estimate Common Neighbor for Link Prediction
• FakeEdge: Alleviate Dataset Shift in Link Prediction
• How Powerful are K-hop Message Passing Graph Neural Networks
• Pairwise Learning for Neural Link Prediction
• How Attentive are Graph Attention Networks?
• Learning Transferable Visual Models From Natural Language Supervision
• On the Bottleneck of Graph Neural Networks and its Practical Implications
• SIGN: Scalable Inception Graph Neural Networks
• How Powerful are Graph Neural Networks?
• Attention Is All You Need
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Geometric Deep Learning: Going beyond Euclidean data
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Conditional Deep Learning for Energy-Efficient and Enhanced Pattern\n Recognition
• Distributed Representations of Words and Phrases and their Compositionality
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Related

• Scalable and Weakly Supervised Bank Transaction Classification
• Improved Customer Transaction Classification using Semi-Supervised Knowledge Distillation
• DeepTrax: Embedding Graphs of Financial Transactions
• Learning Transactions Representations for Information Management in Banks: Mastering Local, Global, and External Knowledge
• Relational Deep Learning: Graph Representation Learning on Relational Databases