Can AI really beat the house in a game mathematically designed for the casino to win? Over the course of 100,000 simulated bets, I set out to test that question — by building and training reinforcement learning agents to outplay American-style roulette. This is the launchpad for a 5-part blog series where I explore the math, psychology, and algorithms behind roulette strategies — from classic betting systems to...
Why I Did This I’ve been experimenting with automation and AI for a while, and I wanted to see if I could create a fully autonomous blog publishing system — one that generates content, adds SEO metadata, creates visuals, and publishes to WordPress without me lifting a finger. This post documents a real test: 11 blog posts, created and published in one day, entirely by a Python-based AI...
Ever wanted your Python scripts to run automatically — every hour, every morning, or after reboot? You don’t need to keep your terminal open or build a full app for that. Windows Task Scheduler can handle it for you — and you can even run your scripts silently in the background. In this post, we’ll cover: Step 1: Yes, You Can Schedule Python Scripts! Windows Task Scheduler is...
As options traders and learners, we often talk about the Greeks — delta, gamma, theta, vega, rho, and their second-order cousins like vanna and vomma. But rarely do we get to see how they behave in real time. I built this fully interactive, educational dashboard using Python and Streamlit to help visualize and better understand how these risk measures respond to changing market conditions. The goal?To create something...
After running over 3,500 backtests across every S&P 500 stock, I wanted a better way to explore the data interactively. So I built a Streamlit dashboard where you can filter by: The goal is to quickly compare performance across strategies, spot outliers, and analyze trends. You can view the full app locally or host it. A demo of the streamlit app can be found on YouTube Closing This...
In Part I, we compared rule-based vs reinforcement learning (RL) trading strategies on AAPL using a 2-year backtest of daily data. Now, we’re scaling that idea across all 500+ tickers in the S&P 500. What happens when we apply the same logic to the entire market? We keep the same seven models and run a uniform backtest across all tickers. Our goal: uncover which models are consistently effective,...
This is the first post in a 3-part series where I explore how rule-based logic compares to reinforcement learning (RL) when building trading strategies. We’ll start simple by testing a handful of models on AAPL — one of the most traded stocks in the world — using two years of daily price data from Yahoo Finance. You’ll see how different models behave under the same conditions, and we’ll...
Introduction This final part summarizes trade performance and identifies optimal trade setups. We generate a ranked list of the best opportunities based on historical data. Trade Success Rates by Setup We calculate the average success rate of different trade setups based on entry time, option type, and strike distance. Option Type Moneyness Strike Distance Entry Time % Achieving 5% Profit Call ATM 0 09:31:00 100.0% Call ITM -7...
Introduction In this section, we apply logistic regression and clustering techniques to better understand trade profitability. We analyze whether specific attributes—such as time of entry, moneyness, and strike distance—affect the likelihood of hitting a profit target. We also explore Cohen’s d effect size measurement and perform survival analysis to determine trade longevity. Logistic Regression for Profit Prediction To predict the probability of an option reaching its profit target,...
Overview This post explores whether options reach predefined profit targets and identifies optimal trade entry times. Key Question Explored Key Functions & Outputs Findings from this section inform strategy development, helping traders maximize returns.
All rights are reserved.
