摘要: We present Route Selection Model (RSM), an online data-driven sales route selector to help firms decide on how respond new business opportunities. The system addresses selection (also known as channel selection) determine if the opportunity can be handled by partners, within firm using agents field, or aim close remotely digital sellers. Given a opportunity, RSM recommends optimal with highest win probability predicted machine learning models and provides explanation meaningful clauses. Compared traditional manual passing approach based rules, makes faster more objective recommendations. Our pilot evaluation study shows our recommendations are not only accurate but also interpretable, which is crucial in decision making. main features of are: (1) automatically merges multiple databases produce timely recommendations, (2) allows users navigate through information evidence supports recommendation. In this paper we describe methodology demonstrate functions RSM.
sci-hub.se 参考文章(4)
Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin, "Why Should I Trust You?": Explaining the Predictions of Any Classifier knowledge discovery and data mining. pp. 1135- 1144 ,(2016) , 10.1145/2939672.2939778
Tianqi Chen, Carlos Guestrin, XGBoost: A Scalable Tree Boosting System knowledge discovery and data mining. pp. 785- 794 ,(2016) , 10.1145/2939672.2939785
Tie-Yan Liu, Taifeng Wang, Thomas Finley, Weidong Ma, Qi Meng, Qiwei Ye, Guolin Ke, Wei Chen, LightGBM: a highly efficient gradient boosting decision tree neural information processing systems. ,vol. 30, pp. 3149- 3157 ,(2017)
Su-In Lee, Scott M. Lundberg, A unified approach to interpreting model predictions neural information processing systems. ,vol. 30, pp. 4768- 4777 ,(2017)