Subject to: Dimitris Bertsimas

Subject to: Dimitris Bertsimas

服務和計畫 (Service and Projects)

政府計畫 (Government Project)

• 國科會，高維度受限迴歸模型與稀疏特徵選取：快速座標下降演算法和應用 (High-Dimensional Constrained Regression Models and Sparse Feature Selection: Fast Coordinate Descent Algorithms and Applications)，主持人 (PI)，115 年度 (2026/8 - 2027/7)
• 國科會，公平最佳決策樹和其應用 (Fair and Optimal Decision Tree and Its Applications)，主持人 (PI)，114 年度 (2025/8 - 2026/7)

產學合作 (Industry-Academia Cooperation)

• 金屬工業研究發展中心 (Metal Industries Research & Development Centre)，最佳化決策於工站排程應用之研究 (Optimal Decision-making in Work Station Scheduling) (3)，主持人 (PI)，2024

Statistical Modeling: The Two Cultures

Cynthia Rudin, Leo Breiman, the Rashomon Effect, and the Occam Dilemma, arXiv:2507.03884, 2025.

In the famous “Two Cultures” paper, Leo Breiman provided a visionary perspective on the cultures of “data models” (modeling with consideration of data generation) versus “algorithmic models” (vanilla machine learning models). I provide a modern perspective on these two approaches. One of Breiman’s key arguments against data models is what he called the “Rashomon Effect,” which is the existence of many different-but-equally-good models. The Rashomon Effect implies that data modelers would not be able to determine which model generated the data. Conversely, one of his core advantages in favor of data models is simplicity, as he claimed there exists an “Occam Dilemma,” i.e., an accuracy-simplicity tradeoff, where algorithmic models must be complex in order to be accurate. After 25 years of more powerful computers, it has become clear that this claim is not generally true, in that algorithmic models do not need to be complex to be accurate; however, there are nuances that help explain Breiman’s logic, specifically, that by “simple,” he appears to consider only linear models or unoptimized decision trees. Interestingly, the Rashomon Effect is a key tool in proving the nullification of the Occam Dilemma. To his credit though, Breiman did not have the benefit of modern computers, with which my observations are much easier to make.

Neural Coordination and Capacity Control for Inventory Management

C Eisenach, U Ghai, D Madeka, K Torkkola, D Foster, S Kakade, Neural Coordination and Capacity Control for Inventory Management, 2024, arXiv preprint arXiv:2410.02817. (SCOT, Amazon)

Optimization Automates Emergency Department Nurse Scheduling at Hartford Hospital

Liangyuan Na, Jean Pauphilet, Ali Haddad-Sisakht, Louis Raison, Audrey Silver, Patricia Veronneau, Nicole Vogt, Dimitris Bertsimas (2024) Optimization Automates Emergency Department Nurse Scheduling at Hartford Hospital. INFORMS Journal on Applied Analytics.

Generalized Synthetic Control for TestOps at ABI

Luis Costa, Vivek F. Farias, Patricio Foncea, Jingyuan (Donna) Gan, Ayush Garg, Ivo Rosa Montenegro, Kumarjit Pathak, Tianyi Peng, and Dusan Popovic, Generalized Synthetic Control for TestOps at ABI: Models, Algorithms, and Infrastructure, To appear in INFORMS Journal on Applied Analytics (Winner, Daniel H. Wagner Prize 2022)

We describe a novel optimization-based approach– Generalized Synthetic Control (GSC)– to learning from experiments conducted in the world of physical retail. GSC solves a long-standing problem of learning from physical retail experiments when treatment effects are small, the environment is highly noisy and non-stationary, and interference and adherence problems are commonplace. The use of GSC has been shown to yield an approximately 100x increase in power relative to typical inferential methods and forms the basis of a new large-scale testing platform: ‘TestOps’. TestOps was developed and has been broadly implemented as part of a collaboration between Anheuser Busch Inbev (ABI) and an MIT team of operations researchers and data engineers. TestOps currently runs physical experiments impacting approximately 135M USD in revenue every month and routinely identifies innovations that result in a 1-2% increase in sales volume. The vast majority of these innovations would have remained unidentified absent our novel approach to inference: prior to our implementation, statistically significant conclusions could be drawn on only ∼ 6% of all experiments; a fraction that has now increased by over an order of magnitude.

BCG 問題解決力

徐瑞廷 / 作者，黃菁媺 / 文字整理，BCG問題解決力：一生受用的策略顧問思考法，時報文化，2021/09/07

奠基於十多年的策略顧問經驗，本書將帶你一次學會：

．「問對問題」：找到問題痛點，就能對症下藥，藥到病除。

．「解決問題」：學習BCG顧問提供的實用技巧，以徹底解決問題。

．「規劃與管理工作進度」：學會釐清工作任務、明辨工作優先順序等，有利高效工作。

．「準備商用簡報」：簡報必須包含關鍵訊息，以清楚傳達具說服力的重點。

．「與客戶溝通」：嚴謹的準備與籌劃是溝通的關鍵，成功的溝通可以創造雙贏局面。

．「使用定量分析工具」：定量分析可以協助證明假說，也能確實找到具備高度價值的資料。

．「從訪談中獲得資訊」：掌握訪談步調，不僅從對方那裡獲取資訊，也要適時給予資訊。

 也可以參考麥肯錫解決問題的方法。

Risk Exposure Index (REI)

David Simchi-Levi, William Schmidt, and Yehua Wei, From Superstorms to Factory Fires: Managing Unpredictable Supply-Chain Disruptions, Harvard Business Review, 2014.

MIT Forum for Supply Chain Innovation, MIT Professor David Simchi-Levi’s Risk Exposure Index (REI) used by the UN Office for Disaster Risk Reduction: REI methodology beginning to influence thinking beyond the supply chain world, May 2, 2014.

Competing in the Age of AI

Marco Iansiti and Karim R. Lakhani, Competing in the Age of AI, Harvard Business Review, January-February 2020, pp. 61-67.

Some key points: 

Removing Limits to Scale, Scope, and Learning

Strategies are shifting away from traditional differentiation based on cost, quality, and brand equity and specialized, vertical expertise and toward advantages like business network position, the accumulation of unique data, and the deployment of sophisticated analytics. 

Putting AI at the Firm’s Core: One strategy, A clear architecture, The right capabilities, An agile “product” focus, Multidisciplinary governance.

IJAA 50th Anniversary Special Issue

 Special Issue of INFORMS Journal on Applied Analytics: Interfaces/IJAA 50th Anniversary Special Issue

Special Issue — M&SOM 20th Anniversary

Special Issue — M&SOM 20th Anniversary, Volume 22, Issue 1, January-February 2020 (online)

This special issue contains invited and review articles by eminent researchers in the field.

Data-Driven Modeling and Optimization of the Order Consolidation Problem in E-Warehousing

Fatma Gzara, Samir Elhedhli, Ugur Yildiz, and Gohram Baloch, Data-Driven Modeling and Optimization of the Order Consolidation Problem in E-Warehousing,  INFORMS Journal on Optimization, Vol. 2, No. 4, Fall 2020, pp. 273–296. (online pdf)

We analyze data emanating from a major e-commerce warehouse and provided by a third-party warehouse logistics management company to replicate flow diagrams, assess order fulfillment efficiency, identify bottlenecks, and suggest improvement strategies. Without access to actual layouts and process-flow diagrams and purely based on data, we are able to describe the processes in detail and prescribe changes. By investigating the characteristics of orders, the wave-sorting operation, and the order-preparation process, we find that products from different orders are picked in batches for efficiency. Similar products are picked in small containers called totes. Totes are then stored in a buffer area and routed to be emptied of their contents at induction lines. Orders are then consolidated at the put wall, where each order is accumulated in a cubby. This order consolidation process depends on the sequence in which totes are processed and has a huge impact on order-completion time. We, therefore, present a generalization of the parallel machine–scheduling problem that we call the order consolidation problem to determine the tote-processing sequence that minimizes total order completion time. We provide mathematical formulations and devise heuristic and exact solution methods. We propose a fast simulated annealing metaheuristic and a branch-and-price approach in which the subproblems are variants of the single machine-scheduling problem and are solved using dynamic programming. We also devise a new branching rule, compare it against the literature, and test it on randomly generated and industry data. Applied to the data and the warehouse under study, optimizing the order consolidation is found to decrease the completion time of 75.66% of orders and achieve average improvements of up to 28.77% in order consolidation time and 21.92% in cubby usage.

A Nonparametric Approach to Modeling Choice with Limited Data

Vivek F. Farias, Srikanth Jagabathula, and Devavrat Shah, A Nonparametric Approach to Modeling Choice with Limited Data, Management Science, February 2013, Vol. 59, No. 2, pp. 305-322. 

Choice models today are ubiquitous across a range of applications in operations and marketing. Real-world implementations of many of these models face the formidable stumbling block of simply identifying the “right” model of choice to use. Because models of choice are inherently high-dimensional objects, the typical approach to dealing with this problem is positing, a priori, a parametric model that one believes adequately captures choice behavior. This approach can be substantially suboptimal in scenarios where one cares about using the choice model learned to make fine-grained predictions; one must contend with the risks of mis-specification and overfitting/underfitting. Thus motivated, we visit the following problem: For a “generic” model of consumer choice (namely, distributions over preference lists) and a limited amount of data on how consumers actually make decisions (such as marginal information about these distributions), how may one predict revenues from offering a particular assortment of choices? An outcome of our investigation is a nonparametric approach in which the data automatically select the right choice model for revenue predictions. The approach is practical. Using a data set consisting of automobile sales transaction data from a major U.S. automaker, our method demonstrates a 20% improvement in prediction accuracy over state-of-the-art benchmark models; this improvement can translate into a 10% increase in revenues from optimizing the offer set. We also address a number of theoretical issues, among them a qualitative examination of the choice models implicitly learned by the approach. We believe that this paper takes a step toward “automating” the crucial task of choice model selection.

The authors formulated the minimum revenue problem under consumer choices as a linear programming with exponential growing of decision variables in terms of product number. Based on duality, they developed polynomial-time algorithms by using constraint sampling and efficient representation of purchase permutations. Profs. Farias and Shah then founded the company Celect and was later acquired by Nike. Once again, it demonstrates the positive cycle of advanced research and academic-industrial collaboration.

Princeton Consultants Inc.

看到上一篇的新聞，得知他們和 Princeton Consultants 合作。基本上，該公司是使用最佳化以管理和解決企業流程的複雜問題，此方法在歐美企業有廣泛的應用，而且有很好的成效，可以參考他們的顧問項目和合作的公司。 

這一家顧問公司的經營團隊經驗豐富，President and CEO Steve Sashihara 寫了一本書，也有 11 位博士，包含 Dr. Irv Lustig；代表此公司是知識密集的產業，也有能力吸引和保有一流的人才。

聘請的員工來自各種學校和專業，可見他們的教育訓練非常的好。也有其他的優點，例如廣泛的背景和領域知識，有助於和顧客溝通，知道導入企業所需的產業知識，降低溝通成本；另外，多元的學術背景也可以提供解決問題時所需的不同角度和思維，有助於團隊合作。

這樣的管理和用人方式，值得我們思考和學習。

Making Better Fulfillment Decisions on the Fly in an Online Retail Environment

Jason Acimovic and Stephen C. Graves, Making Better Fulfillment Decisions on the Fly in an Online Retail Environment, Manufacturing & Service Operations Management, Volume 17, Issue 1, Winter 2015. (2017 M&SOM Best Paper Award)

We develop a heuristic that makes fulfillment decisions by minimizing the immediate outbound shipping cost plus an estimate of future expected outbound shipping costs (*). These estimates are derived from the dual values of a transportation linear program (LP). In our experiments on industry data, we capture 36% of the opportunity gap assuming clairvoyance, leading to reductions in outbound shipping costs on the order of 1%. These cost savings are achieved without any deterioration in customer service levels or any increase in holding costs.

人工智慧在台灣

陳昇瑋、溫怡玲，人工智慧在台灣：產業轉型的契機與挑戰，天下雜誌，2019

本書作者陳昇瑋是台灣少數跨界產業的科學家，擁有學術與產業的深厚背景，同時也是熱情的AI技術傳教士與人才播種者，以跨域者獨有的視野，致力於推動人工智慧在各產業的深化應用及創新轉型，對於製造、金融、零售與醫療等產業應用尤有獨到之處。 

2017年接受中央研究院廖俊智院長與孔祥重院士的邀請，一同帶領團隊在半年內成功幫助超過十家台灣企業，以AI解決或改善影響發展的重大難題，協助產業在人工智慧技術及應用全面升級，也看見產業導入AI的系統性問題。 

人才、資料、找問題，缺一不可
與其擔憂被取代，我們需要主動了解，立即行動以形塑未來 

他透過在地化的實作與顧問經驗，為台灣而創設台灣人工智慧學校，一年內已為台灣培育超過3,000位AI人才，期能解決AI人才不足的關鍵問題，為台灣產業面對的下一個挑戰舖好基礎。

麥肯錫解決問題的方法

wiki

麥肯錫公司（英語：McKinsey & Company，簡稱麥肯錫）為一所由芝加哥大學會計系教授詹姆斯·麥肯錫創立於芝加哥的管理諮詢公司，營運重點是為企業或政府的高層幹部獻策、針對龐雜的經營問題給予適當的解決方案，有「顧問界的高盛」之稱。

高杉尚孝著，鄭舜瓏譯，麥肯錫問題分析與解決技巧：為什麼他們問完問題，答案就跟著出現了？，大是文化，2019

一、發現問題時，先分類，而非究責
二、將問題轉化成具體課題：
三、找出能解決課題的各種替代方案：
四、接下來運用情境分析，評價替代方案：
五、選出「最適合」（未必最佳）的解決策略，並採取行動（貫徹執行力）。

工業3.5

簡禎富，工業3.5：台灣企業邁向智慧製造與數位決策的戰略，天下雜誌，2019

清華講座教授暨美光講座教授簡禎富，二十多年來他深入產學合作第一線，與台灣各產業龍頭合作，深耕智慧製造和大數據分析的研究結果，指出工業4.0革命的三大願景中，大數據與虛實整合系統只是基礎架構和工具目標，根本目標在於掌握彈性決策的核心能力。

Leveraging Comparables for New Product Sales Forecasting

Lennart Baardman, Igor Levin, Georgia Perakis, and Divya Singhvi, Leveraging Comparables for New Product Sales Forecasting, Production and Operations Management, Volume 27, Issue 12, 06 December 2018, Pages: 2340-2343. (First Prize of the 3rd POMS Applied Research Challenge)

This work develops an accurate, scalable and interpretable forecasting tool calibrated with our industry partners’ data. These characteristics are important to our two major industry partners, one being Johnson & Johnson Consumer Companies Inc., a consumer healthcare manufacturer, the other being a large fashion retailer. In building our tool we are motivated by an approach that has been used by industry practitioners: identify a set of products comparable to the new product, average their historical sales, and use this as a forecast. In line with this approach, we devise a model that uses analytics to jointly cluster products while estimating a regularized regression model for each cluster’s sales.... 

The joint cluster-while-regress model is formulated as a non-linear integer optimization problem that is proven to be NP-hard. However, we use the practical interpretation of our problem to devise a fast algorithm whose iterative steps mimic industry practice.... 

Working in collaboration with two large industry partners, we show that our algorithm results in a 20–70% MAPE improvement and 10–60% WMAPE improvement over several benchmarks used in practice.

Risk-based policies for airport security checkpoint screening (機場安檢檢查站檢查)

L.A. McLay, A.J. Lee, and S.H. Jacobson, Risk-based policies for airport security checkpoint screening, Transportation Science, Volume 44, Issue 3, August 2010, pp. 333-349. (Informs 2018 Impact Prize) 

Passenger screening is an important component of aviation security that incorporates real-time passenger screening strategies designed to maximize effectiveness in identifying potential terrorist attacks. This paper identifies a methodology that can be used to sequentially and optimally assign passengers to aviation security resources. An automated prescreening system determines passengers' perceived risk levels, which become known as passengers check in. The levels are available for determining security class assignments sequentially as passengers enter security screening. A passenger is then assigned to one of several available security classes, each of which corresponds to a particular set of screening devices. The objective is to use the passengers' perceived risk levels to determine the optimal policy for passenger screening assignments that maximize the expected total security, subject to capacity and assignment constraints. The sequential passenger assignment problem is formulated as a Markov decision process, and an optimal policy is found using dynamic programming. The general result from the sequential stochastic assignment problem is adapted to provide a heuristic for assigning passengers to security classes in real time. A condition is provided under which this heuristic yields the optimal policy. The model is illustrated with an example that incorporates data extracted from the Official Airline Guide.