Balancing Supply and Demand: Solving Complex Optimization Problems with Python

karthikavijayanexpts


9

Votes

Description:

For any business, it is imperative to find a balance between the sides of supply and demand, while attempting to maximize the business’s own profit. For example, a business might want to minimize the buying price of inventory from its suppliers and maximize the selling price to its clients. While doing this, it might also want to maximize the client and supplier satisfaction in order to raise its own brand reputation and value. This constitutes a classic optimization problem, and in most real-world cases, the problem is going to be either a multivariate or a multiobjective or both. Achieving the solution to such problems manually, by attempting to balance numbers on a tabular sheet is going to be tedious and ineffective.

In the era of AI and automated systems, such problems can be solved efficiently using machine learning and/or guided search. The mathematical formulation for real-world business optimization problems can get pretty complicated. They need specialized strategies of the likes of particle swarm optimization and genetic algorithms as solvers. In this talk, we take the audience through the journey of formulating a mathematical equivalent to a real world business problem. We present a solution to such problems using evolutionary computing, completely implemented in Python. We will showcase the effectiveness of the solution using performance metrics including accuracy, business uplift and execution time.

Outline of the talk (tentative)

  • Introduction (2 mins)
  • Relevancy of business optimisation problems (3 mins)
  • Explanation of a use case and math formulation (7 mins)
  • Explanation of evolutionary computing and genetic algorithm (5 mins)
  • Solution implementation with Python (8 mins)
  • Q/A (5 mins)

Takeaways

  • Learn about optimisation of real-world problems
  • Insights into nuances of formulating such problems in a tech/math language
  • Understand challenges in building solutions. Why out-of-a-box solvers may not always work in real world scenarios?
  • Learn about Python capabilities in solving such problems

Prerequisites:

Basic understanding of computing and programming

Speaker Info:

Speaker- 1 Dr. Karthika Vijayan is a Solution Consultant at Sahaj Software. She has been conducting research in the field of conversational AI with voice and text data for almost a decade. Her research has been published in several journals and presented at various international conferences. Her expertise includes creating customized solutions for real-world business problems by designing composite machine learning pipelines.

Speaker- 2 Karun Japhet is a tech lead, developer, and quality advocate at Sahaj Software. Over the past decade and a half, he has worked on realizing value for his clients through the creation of highly scalable applications and integration of large enterprise applications. More recently, he's been working on building out petabyte scale insights platforms at low cost.

Speaker Links:

Previous talk links (Karthika Vijayan):

  • https://www.youtube.com/watch?v=kphYc_lvKIk&list=PLkPaq00oPRfzz9O4q06rOL2dHCEX7PQwU&index=18
  • https://www.youtube.com/watch?v=gvJhtBdmUi8&t=897s
  • https://www.youtube.com/watch?v=fTlBvqHfbRI
  • https://youtu.be/-uoUwGpzIL0

Profile links (Karthika Vijayan):

  • https://scholar.google.com/citations?user=fJp6O0UAAAAJ&hl=en
  • https://www.linkedin.com/in/karthika-vijayan/
  • https://www.researchgate.net/profile/Karthika-Vijayan

Previous talks (Karun Japhet): YouTube Playlist: https://www.youtube.com/playlist?list=PLY67XcOB0u1SCXn5Z8ZcMnDJHWV4DuPvV

Profile links (Karun Japhet):

  • https://karun.me/
  • https://www.linkedin.com/in/karunjaphet/

Section: Artificial Intelligence and Machine Learning
Type: Talk
Target Audience: Intermediate
Last Updated: