I wanted to share a forecast model for estimating the weekly storage number issued by EIA. The EIA's number is released on Thursday and my forecasts will be released on Monday. The data sets I use are from EIA (for storage numbers) and NOAA for (weather data).
My method uses machine learning principals, though this model is simple in nature. It can be combined with other models to create a true amazing trading outlook for natural gas.
The model is coded in R using R-Studio, what I consider the go to language for statistics.
Current forecast: -50 for week ending 2015-11-27 to be released on 2015-12-03.