To practice convolutional neural network (CNN) design, I worked on a classification problem that was more challenging than toy datasets but still lightweight enough to train quickly on my local machine. The following details the design of a 3-block CNN architecture and the lessons I learned from training it on clothing image data. Dataset Characteristics…
Tag: NumPy
Vectorization and high-speed numerical operations for complex modeling, including epidemic simulations and profit-maximization solvers.
Compare Stock Returns
This page lets you enter multiple stock tickers (eg. AAPL, MSFT, GOOGL) and even custom portfolio expressions (eg. 0.5*NVDA, 0.25*AMZN, 0.25*KO) and compare their performance against a benchmark (eg. SPY) over any time period. It’s built with Python and Flask on the backend. Data comes from Yahoo Finance via the yfinance library, pandas crunches the…
SOAP: A New Polling Platform
Constructive political criticism online is hard to find. Discussions quickly turn mean, and even minor disagreements can escalate into major arguments. Messages often get lost if one’s audience is too small, and misunderstood words can lead to backlash. That’s where Soap comes in—a new kind of social platform designed to change the way we talk…
TQQQ Trading Algorithm
Developing a successful trading algorithm is about finding the right balance between capturing market gains and managing risks. In this capstone project for the Flatiron School Data Science Bootcamp, I created and refined a QuantConnect trading algorithm that combines a dynamic strategy for SPY with a risk-managed approach for TQQQ. The goal was to optimize…
Space Debris Exploration
This is an exploratory data analysis (EDA) of a Kaggle dataset I made as part of the Flatiron School Data Science Bootcamp. The slides from an associated presentation are available here. 🔗 View on GitHub
Skyrim Alchemy Optimizer
This Jupyter notebook can be used to maximize alchemy profitability using the ingredients you have on hand in The Elder Scrolls V: Skyrim. It uses integer linear programming from scipy.optimize.milp to determine which potions to make, and in what quantities, to maximize total value. It needs a csv file of the ingredients you have with…
Efficient Portfolio
This is a Python implementation of Robert C. Merton’s efficient or minimum-variance portfolio algorithm from the paper An Analytic Derivation of the Efficient Portfolio Frontier (1972). Building on the work of Harry Markowitz, Merton describes a way to assign weights to a list of securities to make a portfolio that has the lowest variance in…
Boolean Network Animation
This page animates the dynamics of a random boolean network, a collection of interconnected binary variables with a rule for determining the next state from the current one. 🔗 network.blakerayvid.com View on GitHub