Explaining machine learning models in sales predictions
作者：
Highlights：
• Uniform and comprehensive explanations for an arbitrary black-box prediction model.
• Interactive what-if analysis for the evaluation of decision options.
• Support for validation and updates of decision makers' mental models.
• Real-world application on a difficult business problem - sales forecasting.
• The real-world business-to-business sales data set used is publicly available.
摘要
•Uniform and comprehensive explanations for an arbitrary black-box prediction model.•Interactive what-if analysis for the evaluation of decision options.•Support for validation and updates of decision makers' mental models.•Real-world application on a difficult business problem - sales forecasting.•The real-world business-to-business sales data set used is publicly available.
论文关键词：Machine learning,Prediction explanation,Intelligent system,Black-box models,B2B Sales forecasting
论文评审过程：Received 13 April 2016, Revised 19 October 2016, Accepted 5 November 2016, Available online 9 November 2016, Version of Record 23 December 2016.
论文官网地址：https://doi.org/10.1016/j.eswa.2016.11.010
