Christine Preisach

Oliver Hennhöfer, Maximilian Kirsch, Christine Preisach

Most anomaly detection systems output scores rather than calibrated decisions, leaving practitioners to choose thresholds heuristically and without clear statistical interpretation. Conformal anomaly detection addresses this limitation by converting anomaly scores into calibrated p-values that are valid under the statistical assumption of data exchangeability, with a growing literature extending this idea beyond that setting. We present 'nonconform', a Python package for applying conformal anomaly detection within existing machine-learning workflows, and use it as the basis for an implementation-grounded introduction to the field. The package integrates with 'scikit-learn', 'pyod', and custom anomaly detectors, and provides a unified interface for calibration, p-value generation, and false discovery rate control. It supports several conformalization strategies, ranging from simple split-conformal calibration to more data-efficient and shift-aware extensions. Through a progression from foundational concepts to advanced conformalization strategies, complemented by code examples, the paper connects the statistical ideas behind conformal anomaly detection to their practical use in 'nonconform'. Empirical results demonstrate that the implemented methods enable statistically principled anomaly detection. Together, the package and exposition aim to make core conformal anomaly detection workflows more accessible and reproducible in experimental and production-oriented settings.

Oliver Hennhöfer, Christine Preisach

Standard conformal anomaly detection provides marginal finite-sample guarantees under the assumption of exchangeability . However, real-world data often exhibit distribution shifts, necessitating a weighted conformal approach to adapt to local non-stationarity. We show that this adaptation induces a critical trade-off between the minimum attainable p-value and its stability. As importance weights localize to relevant calibration instances, the effective sample size decreases. This can render standard conformal p-values overly conservative for effective error control, while the smoothing technique used to mitigate this issue introduces conditional variance, potentially masking anomalies. We propose a continuous inference relaxation that resolves this dilemma by decoupling local adaptation from tail resolution via continuous weighted kernel density estimation. While relaxing finite-sample exactness to asymptotic validity, our method eliminates Monte Carlo variability and recovers the statistical power lost to discretization. Empirical evaluations confirm that our approach not only restores detection capabilities where discrete baselines yield zero discoveries, but outperforms standard methods in statistical power while maintaining valid marginal error control in practice.

Yahya Badran, Christine Preisach

Knowledge Tracing (KT) is concerned with predicting students' future performance on learning items in intelligent tutoring systems. Learning items are tagged with skill labels called knowledge concepts (KCs). Many KT models expand the sequence of item-student interactions into KC-student interactions by replacing learning items with their constituting KCs. This approach addresses the issue of sparse item-student interactions and minimises the number of model parameters. However, we identified a label leakage problem with this approach. The model's ability to learn correlations between KCs belonging to the same item can result in the leakage of ground truth labels, which leads to decreased performance, particularly on datasets with a high number of KCs per item. In this paper, we present methods to prevent label leakage in knowledge tracing (KT) models. Our model variants that utilize these methods consistently outperform their original counterparts. This further underscores the impact of label leakage on model performance. Additionally, these methods enhance the overall performance of KT models, with one model variant surpassing all tested baselines on different benchmarks. Notably, our methods are versatile and can be applied to a wide range of KT models.

Maximilian Kirsch, Jakob Wernicke, Pawan Datta et al.

Climate change has increased the vulnerability of forests to insect-related damage, resulting in widespread forest loss in Central Europe and highlighting the need for effective, continuous monitoring systems. Remote sensing based forest health monitoring, oftentimes, relies on supervised machine learning algorithms that require labeled training data. Monitoring temporal patterns through time series analysis offers a potential alternative for earlier detection of disturbance but requires substantial storage resources. This study investigates the potential of a Deep Learning algorithm based on a Long Short Term Memory (LSTM) Autoencoder for the detection of anomalies in forest health (e.g. bark beetle outbreaks), utilizing Sentinel-2 time series data. This approach is an alternative to supervised machine learning methods, avoiding the necessity for labeled training data. Furthermore, it is more memory-efficient than other time series analysis approaches, as a robust model can be created using only a 26-week-long time series as input. In this study, we monitored pure stands of spruce in Thuringia, Germany, over a 7-year period from 2018 to the end of 2024. Our best model achieved a detection accuracy of 87% on test data and was able to detect 61% of all anomalies at a very early stage (more than a month before visible signs of forest degradation). Compared to another widely used time series break detection algorithm - BFAST (Breaks For Additive Season and Trend), our approach consistently detected higher percentage of anomalies at an earlier stage. These findings suggest that LSTM-based Autoencoders could provide a promising, resource-efficient approach to forest health monitoring, enabling more timely responses to emerging threats.

Yahya Badran, Christine Preisach

Knowledge tracing (KT) models aim to predict students' future performance based on their historical interactions. Most existing KT models rely exclusively on human-defined knowledge concepts (KCs) associated with exercises. As a result, the effectiveness of these models is highly dependent on the quality and completeness of the predefined KCs. Human errors in labeling and the cost of covering all potential underlying KCs can limit model performance. In this paper, we propose a KT model, Sparse Binary Representation KT (SBRKT), that generates new KC labels, referred to as auxiliary KCs, which can augment the predefined KCs to address the limitations of relying solely on human-defined KCs. These are learned through a binary vector representation, where each bit indicates the presence (one) or absence (zero) of an auxiliary KC. The resulting discrete representation allows these auxiliary KCs to be utilized in training any KT model that incorporates KCs. Unlike pre-trained dense embeddings, which are limited to models designed to accept such vectors, our discrete representations are compatible with both classical models, such as Bayesian Knowledge Tracing (BKT), and modern deep learning approaches. To generate this discrete representation, SBRKT employs a binarization method that learns a sparse representation, fully trainable via stochastic gradient descent. Additionally, SBRKT incorporates a recurrent neural network (RNN) to capture temporal dynamics and predict future student responses by effectively combining the auxiliary and predefined KCs. Experimental results demonstrate that SBRKT outperforms the tested baselines on several datasets and achieves competitive performance on others. Furthermore, incorporating the learned auxiliary KCs consistently enhances the performance of BKT across all tested datasets.

Oliver Hennhöfer, Christine Preisach

The requirement of uncertainty quantification for anomaly detection systems has become increasingly important. In this context, effectively controlling Type I error rates ($α$) without compromising the statistical power ($1-β$) of these systems can build trust and reduce costs related to false discoveries. The field of conformal anomaly detection emerges as a promising approach for providing respective statistical guarantees by model calibration. However, the dependency on calibration data poses practical limitations - especially within low-data regimes. In this work, we formally define and evaluate leave-one-out-, bootstrap-, and cross-conformal methods for anomaly detection, incrementing on methods from the field of conformal prediction. Looking beyond the classical inductive conformal anomaly detection, we demonstrate that derived methods for calculating resampling-conformal $p$-values strike a practical compromise between statistical efficiency (full-conformal) and computational efficiency (split-conformal) as they make more efficient use of available data. We validate derived methods and quantify their improvements for a range of one-class classifiers and datasets.

Yahya Badran, Christine Preisach

Knowledge Tracing (KT) aims to predict a student's future performance based on their sequence of interactions with learning content. Many KT models rely on knowledge concepts (KCs), which represent the skills required for each item. However, some of these models are vulnerable to label leakage, in which input data inadvertently reveal the correct answer, particularly in datasets with multiple KCs per question. We propose a straightforward yet effective solution to prevent label leakage by masking ground-truth labels during input embedding construction in cases susceptible to leakage. To accomplish this, we introduce a dedicated MASK label, inspired by masked language modeling (e.g., BERT), to replace ground-truth labels. In addition, we introduce Recency Encoding, which encodes the step-wise distance between the current item and its most recent previous occurrence. This distance is important for modeling learning dynamics such as forgetting, which is a fundamental aspect of human learning, yet it is often overlooked in existing models. Recency Encoding demonstrates improved performance over traditional positional encodings on multiple KT benchmarks. We show that incorporating our embeddings into KT models like DKT, DKT+, AKT, and SAKT consistently improves prediction accuracy across multiple benchmarks. The approach is both efficient and widely applicable.

Yahya Badran, Christine Preisach

Personalized recommendation is a key feature of intelligent tutoring systems, typically relying on accurate models of student knowledge. Knowledge Tracing (KT) models enable this by estimating a student's mastery based on their historical interactions. Many KT models rely on human-annotated knowledge concepts (KCs), which tag each exercise with one or more skills or concepts believed to be necessary for solving it. However, these KCs can be incomplete, error-prone, or overly general. In this paper, we propose a deep learning model that learns sparse binary representations of exercises, where each bit indicates the presence or absence of a latent concept. We refer to these representations as auxiliary KCs. These representations capture conceptual structure beyond human-defined annotations and are compatible with both classical models (e.g., BKT) and modern deep learning KT architectures. We demonstrate that incorporating auxiliary KCs improves both student modeling and adaptive exercise recommendation. For student modeling, we show that augmenting classical models like BKT with auxiliary KCs leads to improved predictive performance. For recommendation, we show that using auxiliary KCs enhances both reinforcement learning-based policies and a simple planning-based method (expectimax), resulting in measurable gains in student learning outcomes within a simulated student environment.

Kenan Weber, Christine Preisach

Common challenges in fault diagnosis include the lack of labeled data and the need to build models for each domain, resulting in many models that require supervision. Transfer learning can help tackle these challenges by learning cross-domain knowledge. Many approaches still require at least some labeled data in the target domain, and often provide unexplainable results. To this end, we propose a supervised transfer learning framework for fault diagnosis in wind turbines that operates in an Anomaly-Space. This space was created using SCADA data and vibration data and was built and provided to us by our research partner. Data within the Anomaly-Space can be interpreted as anomaly scores for each component in the wind turbine, making each value intuitive to understand. We conducted cross-domain evaluation on the train set using popular supervised classifiers like Random Forest, Light-Gradient-Boosting-Machines and Multilayer Perceptron as metamodels for the diagnosis of bearing and sensor faults. The Multilayer Perceptron achieved the highest classification performance. This model was then used for a final evaluation in our test set. The results show, that the proposed framework is able to detect cross-domain faults in the test set with a high degree of accuracy by using one single classifier, which is a significant asset to the diagnostic team.