Me and @alveerraa are building this Inventory Optimization Platform (IOP) for the purpose to enhance supply chain efficiency and profitability by providing a data-driven, automated approach to inventory management. By leveraging data structure algorithms, IOP enables businesses to maintain optimal stock levels, minimize waste from overstocking or stockouts, and streamline warehouse and order fulfillment processes. This empowers companies to reduce operational costs, improve resource allocation, and enhance customer satisfaction by meeting demand more accurately. Ultimately, IOP serves to strengthen business agility and competitiveness in an increasingly dynamic market, fostering sustainable growth and efficiency in supply chain operations.
Hey @devansh22435, your project idea should be posted in this discussion as a comment rather than a separate discussion.
I’m working on a totally different project, but we had a similar problem with finding the best route. At first, we thought about using Dijkstra's algorithm, but then we went with something called A* (A-star). It’s pretty cool because, if you have a good way to guide it, A* can actually find the fastest route faster than Dijkstra’s, especially when there are different priorities or costs.
But here’s the catch: A* only works well if you can give it the right clues, so it doesn’t always fit every situation. I think for inventory or supply chain stuff, if you have set routes or patterns, A* might make things quicker. But if the network is all over the place, Dijkstra’s is probably safer. Has anyone else tried A* or something else for inventory management?
We’re implementing Dijkstra's algorithm in our Inventory Optimization Platform for efficient inventory routing. Has anyone worked with alternative algorithms, like Bellman-Ford or Greedy algorithms, for similar purposes? What benefits or challenges did you find?