Multi-Stream Temporal Fusion for Financial Fraud Detection

• URL: http://arxiv.org/abs/2606.25007v1
• Date: Tue, 23 Jun 2026 17:37:27 GMT
• Title: Multi-Stream Temporal Fusion for Financial Fraud Detection
• Abstract summary: Financial fraud detection in digital banking requires reasoning over multiple heterogeneous event streams.<n>We propose the Multi-Stream Fraud Transformer, a unified architecture that encodes each event stream with independent Transformer encoders.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Financial fraud detection in digital banking requires reasoning over multiple heterogeneous event streams -- transactions, login sessions, risk signals -- that individually appear benign but collectively reveal fraudulent patterns. We propose the Multi-Stream Fraud Transformer (MSFT), a unified architecture that encodes each event stream with independent Transformer encoders and fuses their representations through configurable mechanisms. We conduct a systematic ablation study comparing five fusion strategies: concatenation, gated fusion, time-aware positional encoding, cross-stream attention, and a full combination. On a large-scale dataset (10M users, 1.5% fraud rate) with 85M parameter models, we demonstrate that (1) sequence models significantly outperform gradient-boosted trees operating on aggregated features (0.74 vs. 0.99 AUROC), (2) per-stream encoding is essential -- a single-stream Transformer baseline with matched parameter budget reaches only 0.82 AUROC, an 18-point gap that confirms the multi-stream inductive bias is necessary, (3) time-aware positional encoding achieves the highest discrimination (0.9961 AUROC), (4) gated fusion yields the best precision (0.989) suitable for production deployment, and (5) the risk event stream provides the strongest individual signal contribution. We further validate on proprietary production data from a digital banking platform, showing over 22% relative AUROC improvement over the XGBoost baseline.

Related papers

• A Communication-Theoretic Framework for LLM Agents: Cost-Aware Adaptive Reliability [0.20625936401496228]
  We study reliability techniques for large language models built on large language models (LLMs)<n>We show that each of these reliability techniques is a special case of one of six classical reliability operators.<n>We introduce a cost-nearest-neighbor router whose single Lagrangian knob traverses the quality-cost frontier.
  arXiv  Detail & Related papers  (2026-05-09T19:14:33Z)
• ContractShield: Bridging Semantic-Structural Gaps via Hierarchical Cross-Modal Fusion for Multi-Label Vulnerability Detection in Obfuscated Smart Contracts [0.6936215735722616]
  Smart contracts are increasingly targeted by adversaries using obfuscation techniques to evade vulnerability detection.<n>We propose ContractShield, a robust multimodal framework that correlates multiple complementary features through a three-level fusion.<n>ContractShield simultaneously detects five major vulnerability types with 91 percentage F1-score, outperforming state-of-the-art approaches by 6-15 percentage under adversarial conditions.
  arXiv  Detail & Related papers  (2026-04-03T06:29:34Z)
• Tiny Inference-Time Scaling with Latent Verifiers [56.696619768584675]
  Verifier on Hidden States ( VHS) operates on intermediate hidden representations of Diffusion Transformer (DiT) single-step generators.<n> VHS analyzes generator features without decoding to pixel space, thereby reducing the per-candidate verification cost.<n> VHS achieves a +2.7% improvement on GenEval at the same inference-time budget.
  arXiv  Detail & Related papers  (2026-03-23T19:00:02Z)
• Diffusion-Guided Semantic Consistency for Multimodal Heterogeneity [44.06048719126853]
  Federated learning is severely challenged by non-independent and identically distributed (non-IID) client data.<n>We introduce SemanticFL, a novel framework that leverages the rich semantic representations of pre-trained diffusion models.<n>Our results demonstrate that SemanticFL surpasses existing federated learning approaches, achieving accuracy gains of up to 5.49% over FedAvg.
  arXiv  Detail & Related papers  (2026-03-19T04:44:37Z)
• PRISM: Performer RS-IMLE for Single-pass Multisensory Imitation Learning [51.24484551729328]
  We introduce PRISM, a single-pass policy based on a batch-global rejection-sampling variant of IMLE.<n> PRISM couples a temporal multisensory encoder with a linear-attention generator using a Performer architecture.<n>We demonstrate the efficacy of PRISM on a diverse real-world hardware suite, including loco-manipulation using a Unitree Go2 with a 7-DoF arm D1 and tabletop manipulation with a UR5 manipulator.
  arXiv  Detail & Related papers  (2026-02-02T17:57:37Z)
• HCFT: Hierarchical Convolutional Fusion Transformer for EEG Decoding [9.572621097681646]
  We propose a lightweight decoding framework named Hierarchical Conencephaloal Fusion Transformer (HCFT)<n>HCFT combines dual-branchal encoders and hierarchical Transformer blocks for multi-scale representation.<n>Results show that HCFT achieves 80.83% average accuracy and a Cohen's kappa of 0.6165 on BCI IV-2b, as well as 99.10% sensitivity, 0.0236 false positives per hour, and 98.82% specificity on CHB-MIT.
  arXiv  Detail & Related papers  (2026-01-18T06:36:30Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• AMLNet: A Knowledge-Based Multi-Agent Framework to Generate and Detect Realistic Money Laundering Transactions [3.1459290341742676]
  AMLNet is a knowledge-based multi-agent framework with two coordinated units: a regulation-aware transaction generator and an ensemble detection pipeline.<n>The generator produces 1,090,173 synthetic transactions spanning core laundering phases and advanced typologies.<n>The detection ensemble F1 0.90 adapts to the external SynthAML dataset, indicating architectural generalizability.
  arXiv  Detail & Related papers  (2025-09-15T05:25:46Z)
• Investigating Redundancy in Multimodal Large Language Models with Multiple Vision Encoders [54.03921875874111]
  We show that performance degrades gracefully when selected encoders are masked, revealing pervasive encoder redundancy.<n>We observe strong specialization on tasks like OCR and Chart, where a single encoder can dominate with a CUR greater than 90%.<n>Masking specific encoders can yield up to 16% higher accuracy on a specific task category and 3.6% overall performance boost compared to the full model.
  arXiv  Detail & Related papers  (2025-07-04T02:38:59Z)
• Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy [47.997934291881414]
  Existing mean estimation schemes are usually optimized for $L_infty$ geometry and rely on random rotation or Kashin's representation to adapt to $L$ geometry. We introduce a novel privacy accounting method for the sparsified Gaussian mechanism that incorporates the randomness inherent in sparsification into the DP. Unlike previous approaches, our accounting algorithm directly operates in $L$ geometry, yielding MSEs that fast converge to those of the Gaussian mechanism.
  arXiv  Detail & Related papers  (2024-05-02T03:48:47Z)
• ATM Fraud Detection using Streaming Data Analytics [3.4543720783285052]
  In the study, we proposed ATM fraud detection in static and streaming contexts respectively. In both contexts, RF turned out to be the best model. RF is also empirically proven to be statistically significant than the next-best performing models.
  arXiv  Detail & Related papers  (2023-03-08T23:40:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.