Self-Organizing Time Map: An Abstraction of Temporal Multivariate Patterns

TL;DR

The paper introduces the Self-Organizing Time Map (SOTM), a novel extension of SOM for analyzing and visualizing temporal multivariate patterns, capturing both data and time topology in a two-dimensional map.

Contribution

It adapts the SOM framework to temporal data, enabling exploration of temporal structural changes with new measures and visualizations for real-world applications.

Findings

SOTM effectively visualizes temporal data structures.

The method reveals temporal changes in poverty and welfare indicators.

SOTM preserves topology in both time and data dimensions.

Abstract

This paper adopts and adapts Kohonen's standard Self-Organizing Map (SOM) for exploratory temporal structure analysis. The Self-Organizing Time Map (SOTM) implements SOM-type learning to one-dimensional arrays for individual time units, preserves the orientation with short-term memory and arranges the arrays in an ascending order of time. The two-dimensional representation of the SOTM attempts thus twofold topology preservation, where the horizontal direction preserves time topology and the vertical direction data topology. This enables discovering the occurrence and exploring the properties of temporal structural changes in data. For representing qualities and properties of SOTMs, we adapt measures and visualizations from the standard SOM paradigm, as well as introduce a measure of temporal structural changes. The functioning of the SOTM, and its visualizations and quality and property measures, are illustrated on artificial toy data. The usefulness of the SOTM in a real-world setting is shown on poverty, welfare and development indicators.