Forecasting with the Fokker-Planck model: Bayesian setting of parameter

详细信息    查看全文

• 作者：Chris Montagnon ^{c.montagnon@btinternet.com}
• 关键词：Probability distribution ; Fokker&ndash ; Planck equation ; Bayesian parameter selection ; Stock reduction
• 刊名：Physica A: Statistical Mechanics and its Applications
• 出版年：2017
• 出版时间：1 April 2017
• 年：2017
• 卷：471
• 期：Complete
• 页码：253-262
• 全文大小：831 K
• 卷排序：471

文摘

A probability distribution for the next point in a time series is forecast. This probability distribution is the solution to a Fokker–Planck equation. Methods for choosing a single parameter in this distribution are explored. This method gives up to 28% less stock needed to meet 95% of customer demand.