arrow_back BoF on ML platforms
BoF on Interpretability of ML Models arrow_forward
[BoF] Tackling the complex inter-dependent challenges in transport planning and assignment
Submitted by Venkateshan (@venky1729) via Abhishek Balaji (@booleanbalaji) on Monday, 15 July 2019
Session type: Birds of a Feather session of 1 hour Session type: BOF session of 1 hour
Topics to be discussed:
- Variations in the planning/assignment problem formulation and scope.
- Understanding the interplay of multiple objectives- minimizing SLA/service-time breaches, increasing the efficiency of the system, dealing with worst-case scenarios, heterogeneity of the region/occasion where and when it is deployed.
- Landscape of the theoretical approaches ( eg., solutions using integer linear programming, dynamic programming, NP-complete strategies such as branch-and-bound, computational heuristics, GA/simulated-annealing/tabu-seach, any well-known approximation/asymptotic results ).
- Dealing with erroneous/inaccurate predictions.
As the focus here is on the technical discussion, the drivers would ideally be the ones who’ve worked on designing the automated system for shipment delivery/route optimization and/or implementing the solution in the real-world.
Key takeaways from this session
Learning about the preferred tools and techniques that are being employed to solve routing problems. Is there such a thing as state-of-the-art in this case? Understanding the similarities and differences in problem formulation, issues and performance across the different businesses/firms. Where is the greatest scope for improvement? Who can bring fresh insights in this area?
Anyone interested in technical aspects of logistics problems/optimization or learning about the significant challenges involved in arriving at a desirable solution. People curious about how everything from cab aggregators to food delivery to ecommerce shipment scheduling works in the background.
What this session will not be about
Although the discussion is not intended to go deep into algorithmic details, anyone who strictly wants to avoid technical discussions (for example, understanding trade-off between algorithmic performance and computational complexity) may want to skip it. Also, if people are not particularly interested in optimization problems, then they might want to skip it too unless they are otherwise really interested in the domain.
- Venkateshan K (Flipkart)
- Vaibhav Khandelwal (Shadowfax)
- Jayaram Kasi (Pikkol)
- Rahul Jain (Locus)