Date of Award

1-20-2026

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Information Science

First Advisor

Mihail Tudoreanu

Abstract

In this project, we used Topological Data Analysis (TDA) to explore the shape and structure of high-dimensional data and the timeliness dimension of information quality through topological data analysis, with the long-term goal of automatically computing timeliness values that reflect how useful data items are for decision making. The project followed a two-phase approach: in the first half, we employed the Kepler Mapper library along with techniques like Principal Component Analysis (PCA), Uniform Manifold Approximation and Projection (UMAP), T-SNE (t-Distributed Stochastic Neighbor Embedding) and Customized Embedding to analyze and visualize complex datasets. In the second phase, we specifically applied our timeliness assessment to synthetic data because it provides known ground truth for validation, enabling precise evaluation of our method's ability to identify historically relevant data periods. Unlike traditional statistical methods, TDA focuses on understanding the shape and connectivity of data, making it particularly useful for analyzing complex, nonlinear structures. Building on this exploration, in the second half, we focused on determining the timeliness dimension of information quality by applying a modified Mapper algorithm to synthetic datasets. We specifically applied our timeliness assessment to synthetic data because it provides known ground truth for validation, enabling precise evaluation of our method's ability to identify historically relevant data periods based on cyclical patterns. We looked to determine the timeliness value of various portions of the dataset by examining temporal patterns and cyclical behaviors over time.

Download

Included in

Data Science Commons

Share

COinS