Time Series & Quant Trading
From a stationarity test to a backtested trading strategy — time series analysis with an explicit eye toward quantitative trading, beginner to advanced.
TopNotchNote
Notes that matter
coming soon
This track is on the roadmap: what makes time series data different, stationarity and decomposition, classical forecasting (ARIMA/GARCH), walk-forward validation, deep learning for sequences, and the trading-specific back half — market microstructure, feature leakage, backtesting pitfalls, risk management, and execution.
related topics
ML Foundations — the general ML theory this track specializes for sequential, non-i.i.d. data.
Deep Learning & PyTorch Engineering — the RNN/transformer architectures used for sequence modeling here.
GPU Programming & Performance Engineering — vectorized, GPU-accelerated backtesting across strategy parameters.
Deep Learning & PyTorch Engineering — the RNN/transformer architectures used for sequence modeling here.
GPU Programming & Performance Engineering — vectorized, GPU-accelerated backtesting across strategy parameters.