Learning time series prediction-based strategies

Time series prediction-based strategies depend on having a precise estimate of stock prices at some time in the future, along with their corresponding confidence intervals. A calculation of the estimates is usually very time-consuming.

The simple trading rule then incorporates the relationship between the last known price and the future price, or its lower/upper confidence interval value.

More complex trading rules incorporate decisions based on the trend component and seasonality components.

SARIMAX strategy

This strategy is based on the most elementary rule: own the stock if the current price is lower than the predicted price in 7 days:

%matplotlib inline
from zipline import run_algorithm 
from zipline.api import order_target_percent, symbol, set_commission
from zipline.finance.commission import PerTrade
import pandas as pd
import pyfolio as pf
import pmdarima as pm
import warnings
warnings.filterwarnings('ignore...