Serve Robotics Level 4 delivery

Serve Robotics: 新聞

Customer Choice Models vs. Machine Learning

Jacob Feldman, Dennis J. Zhang, Xiaofei Liu, and Nannan Zhang (2021) Customer Choice Models vs. Machine Learning: Finding Optimal Product Displays on Alibaba. Operations Research 70(1):309-328. (Best OM Paper in Operations Research Award: Finalist, pdf, implementation details)

Interesting, Important, and Impactful Operations Management

Gerard P. Cachon, Karan Girotra, Serguei Netessine (2020) Interesting, Important, and Impactful Operations Management. Manufacturing & Service Operations Management 22(1):214-222. 

Learning an Inventory Control Policy with General Inventory Arrival Dynamics

S Andaz, C Eisenach, D Madeka, K Torkkola, R Jia, D Foster, S Kakade, Learning an Inventory Control Policy with General Inventory Arrival Dynamics, 2023, arXiv preprint arXiv:2310.17168. (Amazon)

In this paper we address the problem of learning and backtesting inventory control policies in the presence of general arrival dynamics -- which we term as a quantity-over-time arrivals model (QOT). We also allow for order quantities to be modified as a post-processing step to meet vendor constraints such as order minimum and batch size constraints -- a common practice in real supply chains. To the best of our knowledge this is the first work to handle either arbitrary arrival dynamics or an arbitrary downstream post-processing of order quantities. Building upon recent work (Madeka et al., 2022) we similarly formulate the periodic review inventory control problem as an exogenous decision process, where most of the state is outside the control of the agent. Madeka et al. (2022) show how to construct a simulator that replays historic data to solve this class of problem. In our case, we incorporate a deep generative model for the arrivals process as part of the history replay. By formulating the problem as an exogenous decision process, we can apply results from Madeka et al. (2022) to obtain a reduction to supervised learning. Finally, we show via simulation studies that this approach yields statistically significant improvements in profitability over production baselines. Using data from an ongoing real-world A/B test, we show that Gen-QOT generalizes well to off-policy data.

A Practical End-to-End Inventory Management Model with Deep Learning

Meng Qi, Yuanyuan Shi, Yongzhi Qi, Chenxin Ma, Rong Yuan, Di Wu, Zuo-Jun (Max) Shen (2023) A Practical End-to-End Inventory Management Model with Deep Learning. Management Science 69(2):759-773. (Data and Python codes) 

We investigate a data-driven multiperiod inventory replenishment problem with uncertain demand and vendor lead time (VLT) with accessibility to a large quantity of historical data. Different from the traditional two-step predict-then-optimize (PTO) solution framework, we propose a one-step end-to-end (E2E) framework that uses deep learning models to output the suggested replenishment amount directly from input features without any intermediate step. The E2E model is trained to capture the behavior of the optimal dynamic programming solution under historical observations without any prior assumptions on the distributions of the demand and the VLT. By conducting a series of thorough numerical experiments using real data from one of the leading e-commerce companies, we demonstrate the advantages of the proposed E2E model over conventional PTO frameworks. We also conduct a field experiment with JD.com, and the results show that our new algorithm reduces holding cost, stockout cost, total inventory cost, and turnover rate substantially compared with JD’s current practice. For the supply chain management industry, our E2E model shortens the decision process and provides an automatic inventory management solution with the possibility to generalize and scale. The concept of E2E, which uses the input information directly for the ultimate goal, can also be useful in practice for other supply chain management circumstances.

打造高效AI推薦系統

 蔡銘仁，打造高效AI推薦系統　林永隆率創鑫智慧挺進世界，EE Times Taiwan，2022-10-27

新創公司創鑫智慧僅成軍第三年，首款人人工智慧(AI)加速晶片就採用成本高昂的台積電7nm製程，吸引業界關注；董事長暨執行長林永隆在半導體業界累積近40年的專業資歷，更讓外界對公司的前景抱有高度期待。他們擘劃的宏大願景，是立志成為世界級的AI加速器供應商。...

Data-driven research in retail operations

M. Qi, H.Y. Mak, and Z.J.M. Shen, Data‐driven research in retail operations—A review, Naval Research Logistics, 2020, 67 (8), 595-616. (Open access)

We review the operations research/management science literature on data-driven methods in retail operations. This line of work has grown rapidly in recent years, thanks to the availability of high-quality data, improvements in computing hardware, and parallel developments in machine learning methodologies. We survey state-of-the-art studies in three core aspects of retail operations—assortment optimization, order fulfillment, and inventory management. We then conclude the paper by pointing out some interesting future research possibilities for our community.

Google AdSense 廣告

 本網站的廣告收入將全數捐助公益團體，並將在此公告之。

作業研究的持續改善

下學年要教我喜歡的作業研究。依照往例，再一次更新之前的版本。

第一學期，考慮確定的環境和有限資源下，使用最佳化 (optimization)，以最大化 (例如利潤) 或最小化目標  (例如成本)。第二學期，準備教不確定性環境下，如何分析、最佳化和做決策 (控制)。

Garrett van Ryzin talks about optimization

以前教營收管理的時候，讀了不少哥倫比亞商學院 van Ryzin 教授的文章，其中一篇說，他們的研究是在解決10年後的問題。各位注意喔，是商學院！

最近在讀一本書，某教授寫的序，開頭四個字，就是學用落差。

momo 訂單不延遲心法是什麼

陳宜伶，momo 訂單不延遲心法是什麼？谷元宏獨家解析疫情下電商必勝策略，buzzorange，2021-09-01

供應鏈和選址

谷元宏表示，沒有人能料到疫情，是因為 momo 已先洞察到電商未來兩到三年的大趨勢，所以有預先佈局衛星倉，把最常搶購一空的貨事先備齊。「你會希望消費者上來都是找得到貨的，更要思考有這麼多貨，該怎麼把貨送給客人？」

谷元宏舉例說，在網際網路建立初期，最難處理的技術問題不是演算法，而是「量」，「甚至現在到了逢年過節，火車票難搶也是『量』的問題。」

所以 momo 率先想到的是，「該怎麼解決同一時間蜂擁而來的量，這些量一定要分散，所以我們整個物流的布局就以分散式布局為主。」

Reinforcement Learning for Industrial AI with Pieter Abbeel

The TWIML AI Podcast, Reinforcement Learning for Industrial AI with Pieter Abbeel - #476, 2021/4/20.

Today we’re joined by Pieter Abbeel, a Professor at UC Berkeley, co-Director of the Berkeley AI Research Lab (BAIR), as well as Co-founder and Chief Scientist at Covariant.

In our conversation with Pieter, we cover a ton of ground, starting with the specific goals and tasks of his work at Covariant, the shift in needs for industrial AI application and robots, if his experience solving real-world problems has changed his opinion on end to end deep learning, and the scope for the three problem domains of the models he’s building.

We also explore his recent work at the intersection of unsupervised and reinforcement learning, goal-directed RL, his recent paper “Pretrained Transformers as Universal Computation Engines” and where that research thread is headed, and of course, his new podcast Robot Brains, which you can find on all streaming platforms today!

The complete show notes for this episode can be found at twimlai.com/go/476.

Efficient Large-Scale Internet Media Selection Optimization for Online Display Advertising

Courtney Paulson, Lan Luo, and Gareth M. James, “Efficient Large-ScaleInternet Media Selection Optimization for Online Display Advertising,” Journal of Marketing Research, vol. 55, 2018, pp. 489-506. 

In today's digital market, the number of websites available for advertising has ballooned into the millions. Consequently, firms often turn to ad agencies and demand-side platforms (DSPs) to decide how to allocate their Internet display advertising budgets. Nevertheless, most extant DSP algorithms are rule-based and strictly proprietary. This article is among the first efforts in marketing to develop a nonproprietary algorithm for optimal budget allocation of Internet display ads within the context of programmatic advertising. Unlike many DSP algorithms that treat each ad impression independently, this method explicitly accounts for viewership correlations across websites. Consequently, campaign managers can make optimal bidding decisions over the entire set of advertising opportunities. More importantly, they can avoid overbidding for impressions from high-cost publishers, unless such sites reach an otherwise unreachable audience. The proposed method can also be used as a budget-setting tool, because it readily provides optimal bidding guidelines for a range of campaign budgets. Finally, this method can accommodate several practical considerations including consumer targeting, target frequency of ad exposure, and mandatory media coverage to matched content websites.

Algorithm: Coordinate descent algorithm for budget optimization problem (7).

咖啡廳裡親子的對話

 有一天，在咖啡廳裡工作，聽到隔壁一對父母在教小孩。

大概的情況是，小孩子的作業訂正有問題，媽媽非常地生氣，期間也說明別人是如何如何，為什麼你都做不好？小孩子低聲啜泣，對媽媽的話，也不太敢反駁。爸爸則是說，我們不是和乞丐比較，唸書是要幫你找到好工作、賺錢 。後來，我和小孩剛好都離座，在走道上，我仔細地看了小孩一眼，一看就是一個乖巧、懂事的小孩子。回座後，夫妻開始有不同的意見。前後超過一個小時。

當下有非常高的衝動，想要和父母講一下。但是，我怕被白眼，所以還是忍了下來。

周品均抓出團隊痛點讓美妝品牌從大虧到盈利

程倚華，別人不敢她敢！周品均上任唯品風尚CEO抓出團隊哪6大痛點，讓這家美妝品牌從大虧到盈利？，數位時代，2021.01.22

問題1：廣告策略

周品均觀察，起初，4大美妝品牌的廣告費佔了營收將近40%，ROAS（Return On Ad Spend，目標廣告支出回報率）卻只有0.8～1.1。

台積電的數位轉型

王宏仁，台積電數位轉型的下一步，靠AI推動全面轉型（上），iThome，2021-01-27

IT，就是讓台積順利將各種製造服務轉為自動化的關鍵。在1996年，台積為了將後勤和財務資訊轉換成管理資訊來輔助決策，展開了資訊系統大升級，當年WWW技術才剛點燃了全球網際網路新浪潮不久，台積就能運用當時的網路技術，推出了全方位訂單管理系統，讓顧客透過電腦網路連線取得訂單和產品生產資訊，這也是半導體代工產業的創舉。1999年更推出供應鏈管理的資訊服務，可以讓客戶透過網路下單、即時查詢晶片生產進度和出貨狀況，早在30年前，台積電就採取了現在網路電商慣用的銷售形式。...

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.

Information Rules (資訊經營法則)

C. Shapiro and H.R. Varian, Information Rules: A Strategic Guide to the Network Economy, Harvard Business School Press, 1998.
張美惠翻譯，資訊經營法則，時報出版，2000

In Information Rules, authors Shapiro and Varian reveal that many classic economic concepts can provide the insight and understanding necessary to succeed in the information age. They argue that if managers seriously want to develop effective strategies for competing in the new economy, they must understand the fundamental economics of information technology. Whether information takes the form of software code or recorded music, is published in a book or magazine, or even posted on a website, managers must know how to evaluate the consequences of pricing, protecting, and planning new versions of information products, services, and systems. The first book to distill the economics of information and networks into practical business strategies, Information Rules is a guide to the winning moves that can help business leaders navigate successfully through the tough decisions of the information economy.

本書歸納的經濟法則歷久彌新，值得推薦給學生和專業人士了解。

Chapter 1 of Information Rules begins with a description of the change brought on by technology at the close of the century--but the century described is not this one, it's the late 1800s. One hundred years ago, it was an emerging telephone and electrical network that was transforming business. Today it's the Internet. The point? While the circumstances of a particular era may be unique, the underlying principles that describe the exchange of goods in a free-market economy are the same.

SIAM Conference on Mathematics of Data Science (MDS20)

 SIAM Conference on Mathematics of Data Science (MDS20)  Topological Data Analysis of Complex High-Dim. Layout Configurations for IC Physical Designs