PADD5 EIA Forecasting Using Machine Learning Techniques

使用机器学习技术进行 PADD5 EIA 预测

• 批准号: 514712-2017
• 负责人: Liu, Zheng
• 金额: $ 1.77万
• 依托单位: University of British Columbia
• 依托单位国家: 加拿大
• 项目类别: Engage Grants Program
• 财政年份: 2017
• 资助国家: 加拿大
• 起止时间: 2017-01-01 至 2018-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=640346
• 关键词: PADD5; EIA; Forecasting; Using; Machine

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.

对最佳交易决策的支持对于汽油、喷气式飞机和柴油产品市场至关重要。利用“库存水平”信息可以帮助客户在市场前优化交易决策。Navarik是一家位于温哥华的软件公司，专门从事石油和天然气行业，并开发了Navarik Inspection平台，以提高贸易结算操作的速度和效率。与Navarik合作，这项研究是为了在Navarik Inspection平台上创建预测功能，并帮助Navarik扩展其贸易结算业务。目标是在EIA（能源信息管理局）结果公布之前预测PADD5（国防区石油管理局5区）的库存水平。本研究将使用Navarik数据、公共数据和第三方数据开发机器学习模型，用于库存水平预测。预测算法将在Microsoft Azure平台上实施，并纳入Navarik Inspection平台，以服务于石油和天然气贸易市场的客户。