@finance.thomas: 1. Start with market math, not complex models Begin with returns, log returns, volatility and correlation. Pull historical data and calculate rolling volatility and drawdowns. If you don’t understand how risk behaves numerically, you can’t think like a quant. 2. Learn probability before machine learning Understand distributions, expected value and variance. Simulate random walks and compare them to real market data. This teaches you why markets cluster in volatility and don’t behave like simple Gaussian models. 3. Build your first signal Code a basic momentum or mean reversion strategy and backtest it properly. Use walk-forward testing and include transaction costs. The goal is not performance, it is understanding robustness. 4. Study risk through stress periods Test your strategy during crisis periods like 2008, 2020 or inflation spikes. If it collapses, you learn more than from a smooth equity curve. Quants think in survival first. 5. Combine signals and control exposure Once you understand one signal, layer volatility targeting or correlation filters. Learning how signals interact is the real transition from beginner to systematic thinker.

Finance.Thomas

Open In TikTok:

Region: PR

Wednesday 25 February 2026 03:05:59 GMT