中文题目：JANOS：集成预测和优化建模的决策框架

报告题目：JANOS: Integrated Predictive and Prescriptive Modeling Framework

主 持 人：王洪鹏  副教授

报 告 人：黄   腾   博士

报告时间：2023年11月28日（星期二）19:30

报告地点：腾讯会议 （会议ID：526-660-758）

报告简介：

商业研究实践见证了预测建模和规范分析整合的激增。本研究描述一个建模框架JANOS，它无缝集成了两个分析流派，允许研究人员和从业者将机器学习模型嵌入到端到端优化框架中，JANOS 允许使用标准优化建模元素（例如约束和变量），其关键的新颖性在于提供建模构造，该构造能够在优化模型中指定常用的预测模型，将预测模型的特征作为优化模型中的变量，并将预测模型的输出合并为目标的一部分。该框架考虑两组决策变量：常规变量和预测变量。常规变量和预测变量之间的关系由用户指定为预训练的预测模型。JANOS 目前支持线性回归、逻辑回归和具有修正线性激活函数的神经网络。在本研究中，我们通过学生入学问题中的奖学金分配示例展示了该框架的灵活性并评估其表现。

Business research practice is witnessing a surge in the integration of predictive modeling and prescriptive analysis. We describe a modeling framework JANOS that seamlessly integrates the two streams of analytics, allowing researchers and practitioners to embed machine learning models in an end-to-end optimization framework. JANOS allows for specifying a prescriptive model using standard optimization modeling elements such as constraints and variables. The key novelty lies in providing modeling constructs that enable the specification of commonly used predictive models within an optimization model, have the features of the predictive model as variables in the optimization model, and incorporate the output of the predictive models as part of the objective. The framework considers two sets of decision variables: regular and predicted. The relationship between the regular and the predicted variables is specified by the user as pretrained predictive models. JANOS currently supports linear regression, logistic regression, and neural network with rectified linear activation functions. In this paper, we demonstrate the flexibility of the framework through an example on scholarship allocation in a student enrollment problem and provide a numeric performance evaluation.

报告人简介：

黄腾，中山大学学院助理教授，研究重点是整合机器学习和优化，设计考虑不确定性和不完美数据的决策方法并推广应用。研究成果发表在Production and Operations Management、INFORMS Journal on Computing等期刊，主持国家自然科学基金项目。

【代表性科研成果】

[1]    Bergman, D., Huang, T., Brooks, P., Lodi, A., and Raghunathan, A. U. (2022). JANOS: An Integrated Predictive and Prescriptive Modeling Framework. INFORMS Journal on Computing, 34(2):807-816. https://doi.org/10.1287/ijoc.2020.1023

[2]    Serra, T., Huang, T., Raghunathan, A. U., and Bergman, D. (2022). Template-based Minor Embedding in Chimera Graphs for Adiabatic Quantum Optimization. INFORMS Journal on Computing, 34(1):427-439. https://doi.org/10.1287/ijoc.2021.1065

[3]    Huang, T., Bergman, D., & Gopal, R. (2019). Predictive and Prescriptive Analytics for Location Selection of Add-on Retail Products. Production and Operations Management, 28(7), 1858-1877.