One of the most important things in trading is figuring out where the price is going in the next few seconds, minutes or hours.
After all, you’re unlikely to make money without an “edge” that gives you an advantage over the market. So let me briefly introduce you to ARIMA (“Auto-Regressive Integrated Moving Average”) modeling.
Used properly, ARIMA lets you forecast prices with a higher degree of accuracy than without it. It’s also very flexible: ARIMA encompasses random-walk and random-trend models, autoregressive models, and exponential smoothing models. Constant trends, linear trends and quadratic trends can all modeled effectively.
You don’t have to start from scratch, though.
In R, the stats package includes an ARIMA function which includes seasonal factors, an intercept term, and exogenous variables (xreg, called “external regressors”).
The “forecast” package in R can also automatically select an ARIMA model for a given time series with the auto.arima() function. The package can even simulate seasonal and non-seasonal ARIMA models with its simulate.Arima() function.
Woud you like to find out how to use all these functions, up to and including the R source code?
I’m publishing another walkthrough video that covers everything you need to know to start using ARIMA quickly.
Get everything now:
Learn about the rest of Premium benefits including our HFT and Algo Development courses, software tool kits, and more!
P.S. I’ve been creating several other walkthoughs including volatility forecasting using GARCH. Risk management and asset allocation are key principles for any serious quant trader. And if you’re interested in any kind of options trading — many quant traders are! — GARCH’s volatility forecasting is absolutely essential.
Get the GARCH video walkthrough too future videos on Stochastic Volatility … Markov Chain … Bootstrapping … Dynamic Linear Modeling … and more!FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!