Project 2: Kernel Regression Models

Kernel regression is a non-parametric technique that is useful when the distribution of the observed data is unknown. In this project, I wrote two univariate kernel regression models: Gaussian Kernel and Epanechnikov Kernel. The two models were compared to a multi-dimensional Kernel in terms of prediction accuracy. Comparison of Gaussian and Epanechnikov Kernel Models Link to project 2

August 4, 2021

Project 5: GARCH Models

Generalized AutoRegressive Conditional Heteroskedasticity (GARCH) models are good for times series data that are very volatile. In this project, I developed and made predictions with different GARCH models using Apple stock prices. Time series chart Link to project 5

August 3, 2021

Project 4: Support Vector Machines (SVM)

A Support Vector Machine (SVM) can be imagined as a surface that defines a boundary between various points of data which represent examples plotted in multidimensional space according to their feature values. The goal of an SVM is to create a flat boundary, called a hyperplane, which leads to fairly homogeneous partitions of data on either side. In this project, I showed some examples of SVM using Quadratic Programming. Plots of exponential loss when delta = 1; 0.