# Interpretable Transformation and Analysis of Timelines through Learning via Surprisability

arXiv: https://arxiv.org/abs/2503.04502 · HTML: https://mlsanity.com/paper/2503.04502/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 124 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Builds on (most cited first, 23 of 23)

- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [Graph Neural Network-Based Anomaly Detection in Multivariate Time Series](https://mlsanity.com/paper/2106.06947/) (2021)
- [MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks](https://mlsanity.com/paper/1901.04997/) (2019)
- [Efficient GAN-Based Anomaly Detection](https://mlsanity.com/paper/1802.06222/) (2018)
- [Toward Supervised Anomaly Detection](https://mlsanity.com/paper/1401.6424/) (2014)
- [One-Class Convolutional Neural Network](https://mlsanity.com/paper/1901.08688/) (2019)
- [An Overview on Data Representation Learning: From Traditional Feature Learning to Recent Deep Learning](https://mlsanity.com/paper/1611.08331/) (2016)
- [Feature-based time-series analysis](https://mlsanity.com/paper/1709.08055/) (2017)
- [On the Nature and Types of Anomalies: A Review of Deviations in Data](https://mlsanity.com/paper/2007.15634/) (2020)
- [The Backbone Method for Ultra-High Dimensional Sparse Machine Learning](https://mlsanity.com/paper/2006.06592/) (2020)
- [Online Multivariate Anomaly Detection and Localization for High-dimensional Settings](https://mlsanity.com/paper/1905.07107/) (2019)
- [Constant State of Change: Engagement Inequality in Temporal Dynamic Networks](https://mlsanity.com/paper/1910.01722/) (2019)
- [Domain-based Latent Personal Analysis and its use for impersonation detection in social media](https://mlsanity.com/paper/2004.02346/) (2020)
- [Using a Power Law Distribution to describe Big Data](https://mlsanity.com/paper/1509.00504/) (2015)
- [Exploration-Exploitation Model of Moth-Inspired Olfactory Navigation](https://mlsanity.com/paper/2312.11492/) (2023)
- [Transfer Learning from an Auxiliary Discriminative Task for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1912.02864/) (2019)
- [Analysis of the competition among viral strains using a temporal interaction-driven contagion model](https://mlsanity.com/paper/2203.08115/) (2022)
- [Can We Mathematically Spot Possible Manipulation of Results in Research Manuscripts Using Benford's Law?](https://mlsanity.com/paper/2307.01742/) (2023)
- [Assessing individual risk and the latent transmission of COVID-19 in a population with an interaction-driven temporal model](https://mlsanity.com/paper/2307.05840/) (2023)
- [Pulling the Carpet Below the Learner's Feet: Genetic Algorithm To Learn Ensemble Machine Learning Model During Concept Drift](https://mlsanity.com/paper/2412.09035/) (2024)
- [Tighten The Lasso: A Convex Hull Volume-based Anomaly Detection Method](https://mlsanity.com/paper/2502.18601/) (2025)

## Built on by (most cited first, 1 of 1)

- [DiSCo: Making Absence Visible in Intelligent Summarization Interfaces](https://mlsanity.com/paper/2601.07229/) (2026)

## Abstract (arXiv)

The analysis of high-dimensional timeline data and the identification of outliers and anomalies is critical across diverse domains, including sensor readings, biological and medical data, historical records, and global statistics. However, conventional analysis techniques often struggle with challenges such as high dimensionality, complex distributions, and sparsity. These limitations hinder the ability to extract meaningful insights from complex temporal datasets, making it difficult to identify trending features, outliers, and anomalies effectively. Inspired by surprisability -- a cognitive science concept describing how humans instinctively focus on unexpected deviations - we propose Learning via Surprisability (LvS), a novel approach for transforming high-dimensional timeline data. LvS quantifies and prioritizes anomalies in time-series data by formalizing deviations from expected behavior. LvS bridges cognitive theories of attention with computational methods, enabling the detection of anomalies and shifts in a way that preserves critical context, offering a new lens for interpreting complex datasets. We demonstrate the usefulness of LvS on three high-dimensional timeline use cases: a time series of sensor data, a global dataset of mortality causes over multiple years, and a textual corpus containing over two centuries of State of the Union Addresses by U.S. presidents. Our results show that the LvS transformation enables efficient and interpretable identification of outliers, anomalies, and the most variable features along the timeline.