您当前的位置:首页 >> 用图
机器学习改进供应链的十种方法
发布时间:2019-08-29
 

企业使用机器学习技术可以在今时今日实现两位数的增长。这些革命供应链管理的场景包括:预测错误率,按需调节生产力;节省成本指出,及时的交付等等方面。

机器学习的算法和模型基于从大数据集中发现异常,模式乃至预判。许多供应链挑战都离不开时间、成本和资源等要素的制约,这使得机器学习成为解决这些问题的理想技术。

无论是亚马逊机器人系统(仓储自动化机器人)通过机器学习提升准确率,速度和规模;还是DHL依赖AI和机器学习技术赋能其可预测性网络管理系统——一套从内部数据的58个要素中寻找出影响交期延迟首要因素的系统,都通过机器学习定义了下一代供应链管理系统。Gartner预测,到2020年将有95%的SCP(Supply Chain Planning)厂商将在其解决方案中纳入机器学习技术。而2023年,智能算法,AI技术将嵌入超过25%的供应链技术解决方案。

以下是机器学习影响供应链管理的十种场景

1)以机器学习为基础的算法将成为下一代物流技术的基础,通过先进的资源调配系统带来重大收益。

机器学习改进供应链的十种方法


图片来源:MCKINSEY & COMPANY, AUTOMATION IN LOGISTICS: BIG OPPORTUNITY, BIGGER UNCERTAINTY, APRIL 2019. BY ASHUTOSH DEKHNE, GREG HASTINGS, JOHN MURNANE, AND FLORIAN NEUHAUS

2)物联网传感器,新型信息通讯技术,智能运输系统,交通数据将构成宽广的数据集变量,这些内容将通过机器学习技术为供应链改善提供价值。

机器学习改进供应链的十种方法


图片来源:KPMG, SUPPLY CHAIN BIG DATA SERIES PART 1

3)机器学习有机会帮助物流系统节省每年600万美金的成本,这将通过从IoT设备采集的轨迹数据中学习模型来实现

机器学习改进供应链的十种方法


图片来源:BOSTON CONSULTING GROUP, PAIRING BLOCKCHAIN WITH IOT TO CUT SUPPLY CHAIN COSTS, DECEMBER 18, 2018, BY ZIA YUSUF , AKASH BHATIA , USAMA GILL , MACIEJ KRANZ, MICHELLE FLEURY, AND ANOOP NANNRA

4)通过机器学习减少预测错误

通过机器学习技术可以减少因库存不足造成的销售损失,最多可以降低65%。而在库存的准备上也有20%-50%的优化空间。

机器学习改进供应链的十种方法


图片来源:DIGITAL/MCKINSEY, SMARTENING UP WITH ARTIFICIAL INTELLIGENCE (AI) - WHAT’S IN IT FOR GERMANY AND ITS INDUSTRIAL SECTOR? (PDF, 52 PP., NO OPT-IN).

5)DHL研究发现,机器学习技术将帮助物流和供应链单元优化库存占用情况,提升用户体验,减少风险和开发新商业模式。

机器学习改进供应链的十种方法


图片来源:SOURCE: DHL TREND RESEARCH, LOGISTICS TREND RADAR, VERSION 2018/2019 (PDF, 55 PP., NO OPT-IN)

6)一家区域制造商正在使用AI技术来检测和应对不一致的供应商质量等级和交付情况

机器学习改进供应链的十种方法


图片来源:MICROSOFT, SUPPLIER QUALITY ANALYSIS SAMPLE FOR POWER BI: TAKE A TOUR, 2018

7)减少欺诈的潜在风险,改善产品和流程质量

机器学习改进供应链的十种方法


图片来源:FORBES, HOW MACHINE LEARNING IMPROVES MANUFACTURING INSPECTIONS, PRODUCT QUALITY & SUPPLY CHAIN VISIBILITY, JANUARY 23, 2019

8)通过增强端对端的供应链透明度,帮助企业更快响应

机器学习改进供应链的十种方法


图片来源:CHAINLINK RESEARCH, HOW INFOR IS HELPING TO REALIZE HUMAN POTENTIAL,

9)减少特权规则的使用来带的安全风险

首席信息官们正在解决供应链中的特权滥用问题,如果机器学习发现活动的环境处于风险当中,将要求更强力的许可来授权活动。

10)通过机器学习技术,结合IoT数据改善设备的维护水平,降低运营成本。

麦肯锡公司发现,通过机器学习赋能的预测式维护技术,将帮助企业更好地避免机器停止运转。设备的生产力将得以提升20%,而整体维护成本将减少10%。

原文参考资料包括:

Accenture, Reinventing The Supply Chain With AI, 20 pp., PDF, no opt-in.

Bendoly, E. (2016). Fit, Bias, and Enacted Sensemaking in Data Visualization: Frameworks for Continuous Development in Operations and Supply Chain Management Analytics. Journal Of Business Logistics, 37(1), 6-17.

Boston Consulting Group, Pairing Blockchain with IoT to Cut Supply Chain Costs, December 18, 2018, by Zia Yusuf, Akash Bhatia, Usama Gill, Maciej Kranz, Michelle Fleury, and Anoop Nannra

Capgemini, Supply Chain Management – The Quiet Revolution. April 24, 2019

CB Insights, Stocked Up: 150+ Companies Attacking The Supply Chain & Logistics Space, November 30, 2016

Chen, D. Q., Preston, D. S., & Swink, M. (2015). How the Use of Big Data Analytics Affects Value Creation in Supply Chain Management. Journal Of Management Information Systems, 32(4), 4-39.

Council of Supply Chain Management Professionals (CSCMP) Supply Chain Quarterly, Machine learning: A new tool for better forecasting, Joseph Shamir, Q4, 2014

Council of Supply Chain Management Professionals (CSCMP) Supply Chain Quarterly, Paving the way for AI in the warehouse, Luke Waltz Quarter 1 2018 issue

DHL, Artificial Intelligence in Logistics, 2018 (PDF, 45 pp., no opt-in)

DHL, Cracking Logistics with the help of Machine Learning, Harvard Business School, November 13, 2018

DHL, Logistics Trend Radar, 2016 (PDF, 55 pp., no opt-in)

DHL Trend Research, Artificial Intelligence in Logistics, 2018 (PDF, 45 pp., no opt-in)

DHL Trend Research, Logistics Trend Radar, Version 2018/2019 (PDF, 55 pp., no opt-in)

Digital/McKinsey, Smartening up with Artificial Intelligence (AI) - What’s in it for Germany and its Industrial Sector? (PDF, 52 pp., no opt-in)

Feizabadi, J., & Shrivastava, A. (2018). Does AI-enabled demand forecasting improve supply chain efficiency? Supply Chain Management Review, 22(6), 8-10.

Gartner, Supply Chain Trends in the Digital Age, February 17, 2016 (PDF, 9 pp., no opt-in)

Govindan, K., Cheng, T., Mishra, N., & Shukla, N. (2018). Big data analytics and application for logistics and supply chain management. Transportation Research: Part E, 114343-349.

Hahn, G. J., & Packowski, J. (2015). A perspective on applications of in-memory analytics in supply chain management. Decision Support Systems, 7645-52.

IDC, Digital Transformation Drives Supply Chain Restructuring Imperative, July 2017

IDC, Overcoming Supply Chain Complexity with Predictive Logistics, August 2017 (PDF, 8 pp., no opt-in)

Jayant, A. (2013). Evaluation of 3PL Service Provider in Supply Chain Management: An Analytic Network Process Approach. International Journal Of Business Insights & Transformation, 6(2), 78-82.

KPMG, Supply Chain Big Data Series, Part 2. June 2018 (PDF, 14 pp., no opt-in)

Lai, Y., Sun, H., & Ren, J. (2018). Understanding the determinants of big data analytics (BDA) adoption in logistics and supply chain management. International Journal Of Logistics Management, 29(2), 676-703.

Mackelprang, A. W., Robinson, J. L., Bernardes, E., & Webb, G. S. (2014). The Relationship Between Strategic Supply Chain Integration and Performance: A Meta-Analytic Evaluation and Implications for Supply Chain Management Research. Journal Of Business Logistics, 35(1), 71-96.

McKinsey & Company, Automation in logistics: Big opportunity, bigger uncertainty, April 2019. By Ashutosh Dekhne, Greg Hastings, John Murnane, and Florian Neuhaus

McKinsey & Company, Digital supply chains: Do you have the skills to run them?, July 2017.

Digital/McKinsey, Smartening up with Artificial Intelligence (AI) - What’s in it for Germany and its Industrial Sector? (PDF, 52 pp., no opt-in)

McKinsey & Company, Notes from the AI frontier: Modeling the impact of AI on the world economy, September 2018 By Jacques Bughin, Jeongmin Seong, James Manyika, Michael Chui, and Raoul Joshi

Papadopoulos, T., Gunasekaran, A., Dubey, R., & Fosso Wamba, S. (2017). Big data and analytics in operations and supply chain management: managerial aspects and practical challenges. Production Planning & Control, 28(11/12), 873-876.

Schoenherr, T., & Speier-Pero, C. (2015). Data Science, Predictive Analytics, and Big Data in Supply Chain Management: Current State and Future Potential. Journal Of Business Logistics, 36(1), 120-132.

Sharma, V. (2018). Demand forecasting in the cloud: Modern computing meets the forecasting discipline. The Journal of Business Forecasting, 37(3), 4-7,9-10.

Stanford University, Department of Management Science and Engineering, Lectures in Supply-Chain Optimization (PDF, 261 pp., no opt-in)

Tata Consulting Services, Using Machine Learning to Transform Supply Chain Management

The Hackett Group, Analytics: Laying the Foundation for Supply Chain Digital Transformation (PDF, 10 pp., no opt-in)

Tiwari, S., Wee, H., & Daryanto, Y. (2018). Big data analytics in supply chain management between 2010 and 2016: Insights to industries. Computers & Industrial Engineering, 115319-330.

World Economic Forum, Impact of the Fourth Industrial Revolution on Supply Chains (PDF, 22 pgs., no opt-in)

World Economic Forum, Supply Chain 4.0 Global Practices, and Lessons Learned for Latin America and the Caribbean (PDF, 44 pp., no opt-in)