supply chain data science unleashing ai in the business
play

Supply chain data science: Unleashing AI in the business domain - PowerPoint PPT Presentation

Supply chain data science: Unleashing AI in the business domain Jacomine Grobler Department of Industrial Engineering jacominegrobler@sun.ac.za Data science Descriptive analytics Predictive analytics Prescriptive analytics Prescriptive


  1. Supply chain data science: Unleashing AI in the business domain Jacomine Grobler Department of Industrial Engineering jacominegrobler@sun.ac.za

  2. Data science Descriptive analytics Predictive analytics Prescriptive analytics

  3. Prescriptive analytics projects Minimize - Makespan - Queue time Maximize -Customer service Auxilliary Primary Resource Resource Set for Set for O21 O21 O21 O22 O23 O31 O32 O33 O11 O12 O13

  4. Preliminary Results Acknowledgements: Tsietsi Moremi

  5. Data Science Descriptive analytics Predictive analytics Prescriptive analytics

  6. Acknowledgements: Yolandi Le Roux; University of Pretoria

  7. A Predictive Model from the Agricultural Industry Plant type Water Fertilizer Location History Soil type Acknowledgements: Yolandi Le Roux; University of Pretoria

  8. Acknowledgements: Yolandi Le Roux; University of Pretoria

  9. Results 94% accuracy obtained with a random forest algorithm Acknowledgements: Yolandi Le Roux; University of Pretoria

  10. A job shop scheduling problem with due dates: Which rule should we use? Operation 5 • FIFO Operation 6 • EDD Operation 7 • SPT Time (days) Time (days) Time (days) Time (Days) May 2008 Resources 12 13 14 15 16 17 18 19 20 21 22 23 24 25 1 Operation 1 Operation 3 Operation 4 2 Operation 2 Operation 4 3 Operation 1 4 Acknowledgements: M Agigi; University of Pretoria 10

  11. The training data • Five data sets of different sizes • 56, 100, 146, 200, 256-operations • Three algorithms • FIFO, SPT & EDD At each “scheduling decision” the Work in Process (WIP) and Average Remaining Processing time (ARP) was calculated and the best performing algorithm (wrt makespan) was recorded Acknowledgements: M Agigi; University of Pretoria 11

  12. Results Acknowledgements: M Agigi; University of Pretoria

  13. Results • Based on problem size, APT & WIP, the correct rule could be selected with an accuracy of 94% . • Future work can include incorporating more attributes, utilizing a larger dataset and investigating more complex scheduling algorithms.

  14. Collaborative Filter Type Recommender for Incentive Programmes Classify customers into incentive categories KNN clustering to identify similar users Identify recommendations based on all point contributing activities 69% of users ascended in the programme Acknowledgements: Ridhaa Beneveld; University of Pretoria

  15. Customer Segmentation by means of Data Science Unique product service agreements Order qty Location Business rules Credit history $ contribution Payment type Products Complaints Socio- demographics Industry Resource planning Cost 2 serve

  16. Predicting Delivery Times Location Driver Traffic Weather Residence type Order $ Socio- demographics Distance

  17. Predicting Manufacturing Performance Clustering of production processes Classification of processes wrt quality Training & comparison with SPC charts Acknowledgements: Sibusiso Khoza

  18. Other Projects • Predicting port delays from wind, wave and other data • Predicting energy requirements in the hospitality industry • Greenhouse gas prediction • Supply chain performance prediction • Predicting diabetes through medication purchasing data Acknowledgements: Andries Engelbrecht; Cecil Musisinyani; Philip du Plooy; Lumi Dreyer; University of Pretoria

  19. Supply chain data science: Unleashing AI in the business domain Jacomine Grobler Department of Industrial Engineering jacominegrobler@sun.ac.za

Recommend


More recommend