---
title: "BINet: Multi-perspective Business Process Anomaly Classification"
type: source
tags: [anomaly-detection, rnn, ppm-adjacent, multi-perspective]
authors: [Nolle Timo; Luettgen Stefan; Seeliger Alexander; Mühlhäuser Max]
year: 2019
venue: "Information Systems (preprint arXiv:1902.03155v1)"
kind: paper
raw_path: "raw/Predictive process monitoring/BINet - Multi-perspective Business Process Anomaly.pdf"
created: 2026-04-13
updated: 2026-04-13
key_claims:
  - Anomaly detection must work at the event-attribute level, not just case-level, to provide useful diagnostics.
  - BINet (Business Intelligence Network) is an RNN architecture detecting anomalies in both control-flow and data perspectives.
  - A set of heuristics automates the detection threshold — removes user-chosen threshold burden.
  - Evaluated on 29 synthetic + 15 real-life logs; outperforms 8 prior state-of-the-art methods.
---

# Nolle et al. 2019 — BINet: Multi-perspective Anomaly Classification

Extension of Nolle et al.'s 2018 BINet with three architectural variants, automated threshold heuristics, and a rule-based classifier over BINet outputs. **Anomaly detection**, not strictly prediction, but uses the same RNN-based trace modelling as neural [[concepts/predictive-process-monitoring|PPM]].

## Contribution
- **Multi-perspective RNN** — jointly models control-flow and data attributes.
- **Attribute-level detection** — the anomaly is localised to the specific attribute value, not just the case.
- **Runtime deployability** — can train during execution, adapts to concept drift.
- Five assumptions it operates under: no domain knowledge, no clean dataset, no reference model, no labels, no manual threshold — i.e., truly unsupervised.

## Significance
Bridges PPM and anomaly/conformance-adjacent work. Relevant for APM's [[concepts/self-modification|self-modification]] (specifically the "detect misbehaviour" requirement in adaptation triggers) and the benchmark-contamination challenge (C3) in [[sources/2026-calvanese-agentic-bpm-manifesto]].

## Connections
**Concepts:** [[concepts/predictive-process-monitoring]] · [[concepts/self-modification]]
**Authors:** [[entities/timo-nolle]]