Topological Fraud Detection in Latent Transaction Spaces

Avraham Bourla

cs.LGSep 8, 2026

Topological Fraud Detection in Latent Transaction Spaces

Authors: Avraham Bourla

Abstract

Working entirely on topologically anonymized embeddings, we perform fraud detection using iterative rounds of unsupervised filtering followed by supervised sniping. The result is an ultra-low latency privacy--preserving triage that allows institutions to flag suspicious activity without compromising Personally Identifiable Information.

Explore similar work

SilIF: Silhouette-Augmented Isolation Forest for Unsupervised Transaction Fraud Detection
May 21, 2026Venkatakrishnan GopalakrishnanFraud Detection Reconstruction-Based Anomaly Detection
Layout-Aware Representation Learning for Open-Set ID Fraud Discovery
Apr 17, 2026Jinxing Li, Nicholas Ren, Cathy Chang +2Fraud Detection Face Forgery Detection
SR-Fraud: An Outcome-Supervised Reflective LLM Agent Framework for Non-Stationary Payment Fraud Detection
Sep 23, 2026Xuwei Tan, Yao Ma, Xueru ZhangFraud Detection

May 21, 2026 · cs.LGJ/K move · Enter open · S save

SilIF: Silhouette-Augmented Isolation Forest for Unsupervised Transaction Fraud Detection

Venkatakrishnan Gopalakrishnan

Independent Researcher Redmond, WA, USA

Unsupervised anomaly detection is widely used in transaction fraud detection where labels are scarce. Isolation Forest (IF) is among the most popular classical methods due to its scalability and ease of deployment. We propose SilIF, an augmentation of Isolation Forest that adds a silhouette-based scoring layer computed in a representation space induced by the trees of the forest. For each point, we extract a vector of per-tree path lengths, cluster these "fingerprints" into structural groups, and compute a silhouette score that measures how well the point fits its assigned group versus the nearest alternative. The silhouette signal is combined with the base IF score via a single hyperparameter alpha. On the IEEE-CIS Fraud Detection benchmark (~590K transactions, 3.5% fraud), SilIF with alpha=1.0 improves over plain Isolation Forest by +0.0080 AUC-PR on average across five seeds, with SilIF winning on all five seeds (paired t-test p=0.046). We also report results on a synthetic credit-card dataset (Sparkov) where the silhouette augmentation does not improve over plain IF, and we characterize the conditions that distinguish the two outcomes. The paper presents SilIF as a tunable, easy-to-deploy enhancement to Isolation Forest with honest reporting of when it helps and when it does not. Code at https://github.com/venkat15vk/silif-anomaly-detection.

Fraud Detection Reconstruction-Based Anomaly Detection Outliers Unsupervised Intrusion Detection Random Forest False Discovery Rate

Open paper Ask about it PDF

Abstract

Explore similar work

SilIF: Silhouette-Augmented Isolation Forest for Unsupervised Transaction Fraud Detection

Layout-Aware Representation Learning for Open-Set ID Fraud Discovery

SR-Fraud: An Outcome-Supervised Reflective LLM Agent Framework for Non-Stationary Payment Fraud Detection