---
title: "Automating Model Management: A Survey on Metaheuristics for Concept-Drift Adaptation"
type: source
tags: [concept-drift, automl, metaheuristics, genetic-algorithms, particle-swarm, data-stream-mining, model-management, survey]
authors: [Riess, Mike]
year: 2022
venue: "Journal of Data, Information and Management 4:211–229, Springer. DOI: 10.1007/s42488-022-00075-5"
kind: paper
raw_path: "raw/Riess/Riess 2022.pdf"
sources: ["[[sources/2023-riess-phd-thesis-ppm]]"]
key_claims:
  - "Population-based metaheuristics (Genetic Algorithms, Particle Swarm Optimization) dominate the retrieved literature on automated concept-drift adaptation across fields (engineering, CS, managerial decision support, finance, social science)."
  - "Usage of metaheuristics has evolved over 2012–2020 from single AutoML tasks (feature selection, hyper-parameter optimisation) toward Full Model Selection (FMS) in online/streaming settings."
  - "Evaluation practice is weak: 4 of 17 studies do not report class distribution despite using accuracy as sole metric; drift type and pattern are often unreported when real-world data is used."
  - "Recommendation: future studies should evaluate metaheuristics as models themselves and report drift characterisation (type, pattern) alongside performance."
  - "None of the retrieved studies compare different population-based metaheuristics against each other on the same drift task — comparative rigour is absent."
  - "Assumption that ground truth is immediately available after prediction is unrealistic in many operational settings; delayed-label evaluation scenarios are underutilised."
created: 2026-04-20
updated: 2026-04-20
---

# Riess 2022 — Automating Model Management: Metaheuristics for Concept-Drift Adaptation

Open-access survey published in the Journal of Data, Information and Management (Springer), authored during Riess's PhD at [[entities/nmbu|NMBU]]. Forms Paper IV of [[sources/2023-riess-phd-thesis-ppm|his PhD thesis]].

## Summary
The paper reviews literature on using metaheuristics to automate the adaptation of machine-learning models under [[concepts/concept-drift|concept drift]]. The adaptation problem — retraining, reconfiguring, or reselecting a model when the data-generating distribution shifts — is framed as a high-dimensional optimisation problem that is generally intractable for exact methods; metaheuristics (stochastic, heuristic-based search algorithms not requiring perfect information about problem structure) are therefore the natural fit. Five research questions guide the review: (RQ1) which metaheuristics are used; (RQ2) in what application areas; (RQ3) how metaheuristics assist self-adaptation; (RQ4) which drift types are studied; (RQ5) how evaluation is performed.

Methodologically the review uses Google Scholar retrieval with explicit inclusion/exclusion criteria (including a citation-count threshold for pre-2021 work) and qualitatively codes each study by metaheuristic type, AutoML problem type (feature selection, HPO, FMS), drift type (sudden, gradual, recurring, real vs. synthetic) and evaluation methodology.

Key findings: **population-based metaheuristics** (GA, PSO, ant colony, bio-inspired variants) overwhelmingly dominate — plausibly because they parallelise naturally and impose few assumptions on problem structure. Usage evolved from single-task automation (feature selection, HPO) toward **Full Model Selection (FMS)** in online/data-stream settings by 2019–2020. However, evaluation practice is patchy: class distributions are frequently unreported while accuracy is the only metric used, drift types are rarely characterised when real-world data is used, and no study compares multiple population-based metaheuristics against each other on the same drift problem.

Riess recommends that (1) future work treat metaheuristics *as models themselves* for comparative evaluation, (2) drift characteristics (type, pattern, magnitude) be reported alongside performance, and (3) delayed-label scenarios be evaluated more often since immediate ground truth is uncommon in practice.

The paper is theoretically grounded in the CRISP-DM ML lifecycle (with explicit BPMN modelling of it), stream mining theory (Gama et al. 2013; Bifet & Gavaldà 2007), AutoML (Feurer & Hutter 2019), and ML-lifecycle management (Schelter et al. 2018; Vartak & Madden 2018). Di Francescomarino et al. 2018 ([[sources/2018-difrancescomarino-genetic-hpo-ppm]]) and Bose/van der Aalst/Žliobaitė/Pechenizkiy 2011 are cited as BPM-adjacent anchors.

## Connections
- Feeds [[concepts/concept-drift]] as the canonical survey reference in this wiki.
- Paper IV of [[sources/2023-riess-phd-thesis-ppm]].
- Cited by [[sources/2025-riess-jorgensen-brage-benchmark-norwegian-llm]] for the concept-drift motivation of the Norwegian customer-service dialogue benchmark.
- Concepts: [[concepts/concept-drift]], [[concepts/predictive-process-monitoring]].
- Author: [[entities/mike-riess]].
- Related sources: [[sources/2018-difrancescomarino-genetic-hpo-ppm]] (GA for PPM HPO).