PADD5 EIA Forecasting Using Machine Learning Techniques

点击翻译按钮获取中文摘要

The support for optimal trading decision making is critical for the gasoline, jet and diesel product market. Theuse of information from "stock levels" can help customers optimize their trading decisions before the market.Navarik, a Vancouver-based software company, is specialized in the oil and gas industry and has developed aNavarik Inspection platform to increase the speed and efficiency of trade settlement operations.In collaboration with Navarik, this research is to create the forecasting capabilities on the Navarik Inspectionplatform and help Navarik to expand its business in trade settlement. The objective is to forecast stock levels inthe PADD5 (Petroleum Administration for Defense Districts region 5) before the EIA (Energy InformationAdministration) results are released. This research will develop the machine learning models by using theNavarik data, public data, and 3rd party data for stock level forecasting. The forecasting algorithms will beimplemented on Microsoft Azure platform and incorporated into Navarik Inspection platform to serve itscustomers and clients in the oil and gas trade market.