Concept drift
Detecting when a data stream's underlying distribution has moved — including when no labels are available to tell you.
LACE
Bilkent University · BilIR
Machine learning for data that never stops changing.
PhD researcher at Bilkent University, working with Prof. Fazlı Can on models that keep learning after deployment — detecting concept drift, adapting on the fly, and holding accuracy as the distribution moves. Alongside the PhD I build demand forecasting and replenishment models in production, across roughly a million SKU-store pairs.
Research
Read more
Three strands, one question
Online & continual learning
Single-pass architectures that update as data arrives, instead of retraining from scratch on a schedule.
AdaNEN · BELSAdapting foundation models
Keeping large language and time-series foundation models current under temporal drift and delayed supervision.
LLM-OFA
Selected work
All publications
Peer-reviewed publications
-
2026LACE
LACE: Unsupervised Concept Drift Detection in Multi-Label Data Streams Through Label Cluster Evolution
ACM CIKM
An unsupervised concept-drift detector for multi-label streams that cuts detection delay by 63.5% against the previous best unsupervised method, at a 0% missed-detection rate.
DETECTION DELAY −63.5% · 0% MISSED · MULTI-LABEL STREAMS
-
2025LLM-OFA
LLM-OFA: On-the-Fly Adaptation of Large Language Models to Address Temporal Drift Across Two Decades of News
ACM CIKM
An On-the-Fly Adaptation framework and the Adaptimizer optimizer for continually adapting LLMs under temporal drift, evaluated across two decades of news.
2 DECADES OF NEWS · CONTINUAL LLM ADAPTATION
-
2024AdaNEN
A Novel Neural Ensemble Architecture for On-the-Fly Classification of Evolving Text Streams
ACM TKDD
AdaNEN — a neural ensemble for evolving data streams that improves classification accuracy by up to 8.8% across 13 benchmark datasets.
ACCURACY +8.8% · 13 DATASETS · SINGLE-PASS