Machine Learning Trading Strategy with Python

Exploring a way to forecast weekly jobless claims with sarimax model and backtesting a trading strategy that outperforms Nasdaq 100.

SARIMAX (Seasonal Autoregressive Integrated Moving Average with exogenous variables) is a statistical method for modeling time series data that includes both autoregression (AR) and moving average (MA) components to model the dependence structure in the data and incorporate seasonality and exogenous variables. SARIMAX can be used to make both short-term and long-term predictions and is one of the best models to predict macroeconomic data such as the weekly jobless claims, which are released every Thursday at 8:30 AM EST.

That’s exactly what we are focusing on in this article today. We are going to find the best SARIMAX model to fit in terms of Autoregressive and Moving Average orders, as well as Seasonality orders. Then we are going to fit this model and predict in a rolling window the weekly jobless claims figure for 1 week ahead. After we have all the predictions made, we would be able to compare them to the actual number itself and try to form a tradable signal and strategy on Nasdaq intraday 1-minute data. Let’s get into it!