Machine Learning Applications in Supply Chain Management CII Conference on E2E Trimodal Supply chain: Envisioning Collaborative, Cost Centric, Digital & Cognitive Supply Chain 27-29 July, 2016
Dr. Arpan Kumar Kar Chairman – Corporate Relations / Coordinator – Faculty Recruitment
Indian Institute of Technology Delhi
[email protected] | Website | Tech Talk
Emergence of Analytics The computational process of discovering patterns in large data sets using quantitative methods. Finds hidden patterns, relationships in large databases and infer rules to predict future behavior with a probability
Major Categories of Analytics Objectives are Pattern Associations, Clustering, Classification, Regression, Sequence mining, Summarization and Anomaly detection. 03-08-2016
Lecture Presentation | © Dr. A. K. Kar
2
Inventory Management Problem Discovering interesting relations between variables in large databases without attempting to explain them Used to predict patterns of variables based on past patterns on which the tool has been trained upon Looks for popular sets of occurrences of variables (transactions) Does not consider the order of items either within a transaction or across transactions. 03-08-2016
Extremely popular in market basket analysis E.G: If a person buys soap and pen, often he buys shampoo. Rule form: “Antecedent -> Consequent [support, confidence]”.
Association Rule: Soap, Pen -> Shampoo [0.5%, 60%]
Lecture Presentation | © Dr. A. K. Kar
3
SCM : Grouping of SKUs for Inventory Management A stock keeping unit (SKU) is a distinct type of item for sale, such as a product or service with unique attributes like manufacturer, description, material, size, color, packaging, & warranty.
location of manufacturing sites Cost of rejection Design of logistics systems Appropriate inventory levels
The stocking policies Safety factors for each SKU Specification of customer service
● denotes SCN with interactions between suppliers of materials, manufacturers, distributors, transportation links and customers
Specification of performance Srinivasan, M., & Moon, Y. B. (1999). A comprehensive clustering algorithm for strategic analysis of supply chain networks. CIE, 36(3), 615-633.
03-08-2016
Lecture Presentation | © Dr. A. K. Kar
4
Supplier Selection Problem
Product quality Exporting status Product pricing Management capability Labor relations Reciprocal arrangements Inventory position Geographical distance Acceptable parts per mn. Trade restrictions Documentation Rejection rate (inspection) Lead time Innovation Domain experience 03-08-2016
Delivery reliability Packaging capability Production capability Vendor reputation Service quality Cultural fitment EDI Capability Foreign exchange rates Service design Buyer’s commitment Design capability Value of performance Indirect costs Facility planning Exporting status
Kar, A. K. (2015). A hybrid group decision support system for supplier selection using analytic hierarchy process, fuzzy set theory and neural network. Journal of Computational Science, 6, 23-33. Kar, A. K. (2014). Revisiting the supplier selection problem: An integrated approach for group decision support. Expert systems with applications, 41(6), 2762-2771.
Lecture Presentation | © Dr. A. K. Kar
5
The emergence of intelligent techniques
Highest Fitness
Multi-criteria inventory management A company may need over 10,000 commodities in its inventory, each with its own consumption pattern, sourcing and stocking challenges. Problem is to classify them into sets which will have similar management issues (like re-ordering at the same time and if possible, from the same location/source). 03-08-2016
Lecture Presentation | © Dr. A. K. Kar
6
Evolution of computing needs
Kar, A. K. (2016). Bio inspired computing–A review of algorithms and scope of applications. Expert Systems with Applications, 59, 20-32.
03-08-2016
Lecture Presentation | © Dr. A. K. Kar
7
Evolution of Intelligent Systems
Kar, A. K. (2016). Bio inspired computing–A review of algorithms and scope of applications. Expert Systems with Applications, 59, 20-32.
03-08-2016
Lecture Presentation | © Dr. A. K. Kar
8
Scope Analysis Quadrant 1: Zone of Theory Development Quadrant 2: Zone of Applications Amoeba, Artificial plant optimization, Bean Bacterial foraging, Bat algorithm, Artificial bee optimization, Dove, Eagle, Fruit fly, Glow-worm, colony, Cuckoo search, Firefly algorithm, Flower Grey wolf, Krill-herd, Lion, Monkey, Wolf
pollination
Quadrant 3: Zone of Rediscovery
Quadrant 4: Zone of Commercialization
Leaping Frog, Shark, Wasp
Neural Networks, Genetic algorithm, Ant colony optimization, Particle swarm
03-08-2016
Lecture Presentation | © Dr. A. K. Kar
9
Potential Application Domains Supply chain management and Industrial engineering Information Systems Marketing Science Human computer interaction Financial engineering Social network analysis, Telecom Internet of Things, Web 2.0, Search Engines 03-08-2016
Lecture Presentation | © Dr. A. K. Kar
10
Thank you
03-08-2016
Lecture Presentation | © Dr. A. K. Kar
11
Key references Hipp, J., Güntzer, U., & Nakhaeizadeh, G. (2000). Algorithms for association rule mining—a general survey and comparison. ACM sigkdd explorations newsletter, 2(1), 58-64. Srinivasan, M., & Moon, Y. B. (1999). A comprehensive clustering algorithm for strategic analysis of supply chain networks. CIE, 36(3), 615633. Kar, A. K. (2015). A hybrid group decision support system for supplier selection using analytic hierarchy process, fuzzy set theory and neural network. Journal of Computational Science, 6, 23-33. Kar, A. K. (2014). Revisiting the supplier selection problem: An integrated approach for group decision support. Expert systems with applications, 41(6), 2762-2771. Kar, A. K. (2016). Bio inspired computing–A review of algorithms and scope of applications. Expert Systems with Applications, 59, 20-32. Andrieu, C., De Freitas, N., Doucet, A., & Jordan, M. I. (2003). An introduction to MCMC for machine learning. Machine learning, 50(1-2), 543. Goldberg, D. E., & Holland, J. H. (1988). Genetic algorithms and machine learning. Machine learning, 3(2), 95-99. Specht, Donald F. "Probabilistic neural networks." Neural networks 3, no. 1 (1990): 109-118. Ma, B. L. W. H. Y. (1998, August). Integrating classification and association rule mining. In Proceedings of the fourth international conference on knowledge discovery and data mining. Zhang, C., & Zhang, S. (2002). Association rule mining: models and algorithms. Springer-Verlag. Hidber, C. (1999). Online association rule mining (Vol. 28, No. 2, pp. 145-156). ACM. Kar, A. K. (2009). Modeling of supplier selection in e-procurement as a multi-criteria decision making problem. Working Papers on Information Systems ISSN, 1535-6078. Kar, A. K., & De, S. K. (2009). Using neural networks for pattern association for the online purchase of products. Chauhan, S., Agarwal, N., & Kar, A. K. (2016). Addressing Big Data Challenges in Smart Cities: A Systematic Literature Review. info, 18(4). Manyika, J., Chui, M., Brown, B., Bughin, J., Dobbs, R., Roxburgh, C., & Byers, A. H. (2011). Big data: The next frontier for innovation, competition, and productivity. Zikopoulos, P., & Eaton, C. (2011). Understanding big data: Analytics for enterprise class hadoop and streaming data. McGraw-Hill Osborne Media. Provost, F., & Fawcett, T. (2013). Data science and its relationship to big data and data-driven decision making. Big Data, 1(1), 51-59.
03-08-2016
Lecture Presentation | © Dr. A. K. Kar
12
