Locally Linear Embedding
-
- 0 Rating
- 0 Reviews
- 1 Students Enrolled
Locally Linear Embedding
Locally Linear Embedding
-
- 0 Rating
- 0 Reviews
- 1 Students Enrolled
Requirements
- MVA book
General Overview
Description
Locally Linear Embedding (LLE) is a nonlinear dimensionality reduction method that reconstructs each data point from its nearest neighbors and preserves these local relationships in a lower-dimensional embedding. Its goal is to capture the underlying manifold structure of high-dimensional data while maintaining local geometry. Common applications include visualization, manifold learning, and preprocessing for tasks such as clustering or classification.
Recommended for you
Meet the instructors !
Matthias Fengler is a full professor of econometrics at the University of St. Gallen, specializing in financial econometrics. He holds a PhD in Quantitative Finance from Humboldt Universität zu Berlin and has experience as both a quantitative analyst and academic. His research focuses on asset pricing, volatility modeling, and risk management. He has published in leading journals such as the Journal of Econometrics, Journal of Financial Econometrics, and Journal of Banking and Finance, and co-authored the sixth edition of Applied Multivariate Statistical Analysis (Springer). His projects include the award-winning “Monitoring Consumption Switzerland,” and his recent work applies machine learning and alternative data, including textual analysis, to financial forecasting.