Amazon delivers 2.5 Billion packages per year. Without proper planning and optimisation it will be nightmare to manage such a gigantic task. Learn how 'Genetic Algorithm' can be used to optimise routes. Book this live session now....
Amazon has invested $60 billion in building out fulfillment warehouses, leasing airplanes and buying delivery vans. The retailer already delivers half of its own packages and could become a major competitor for the fulfillment business of other e-retailers in the years ahead. Amazon delivers 2.5 Billion packages per year. Without proper planning and optimisation it will be nightmare to manage such a gigantic task.
Typically each delivery person has few packets to deliver but has many combinations he/she can use to complete the delivery. Also, time among destinations fluctuates during the day due to traffic, weather, accidents, or other events. Thus, it is important to recommend a optimised route to delivery person, so that he/she can save time and resources.
A genetic algorithm (GA) is a method for solving both constrained and unconstrained optimization problems based on a natural selection process that mimics biological evolution.
In this session understand optimization problems and how to solve them using Genetic Algorithm.
Amazon.com, Inc. is an American multinational technology company that focuses on e-commerce, cloud computing, digital streaming, and artificial intelligence. The year was 94′ and Bezos was working diligently on Wall Street. At 30 years old, he began to see the internet revolution take place, and made the decision to quit his job and start an internet company.
“The wake-up call was finding this startling statistic that web usage in the spring of 1994 was growing at 2,300 percent a year. You know, things just don’t grow that fast. It’s highly unusual, and that started me thinking, “What kind of business plan might make sense in the context of that growth?”
After making a list of the ‘top 20’ products that he could potentially sell on the internet, he decided on books because of their low cost and universal demand. It turns out, it was just the beginning.....
Apart from putting every product on a single website, the main business of amazon is its logistics. Amazon aims for the day when users will get their placed orders within minutes. Currently, they offer 1-day delivery to few cities. Amazon is one of the new companies that is competing against decades-old logistic companies like DHL, FedEx.
A lot of things happen between placing an order and its delivery. If any step goes wrong, there will be a delay in delivery. Amazon stores nearly all of its products in Amazon Fulfillment Centers. They are large warehouses present in different states.
Whenever a user places an order, it's get packed and get ready to be shipped. After this, the order travels to its next stop "Amazon Sortation Centers". Depending on the distance, either air cargo planes or lorry is used. After which the package gets transported to a delivery station near the customer location. Now, for last-mile connectivity small delivery vans are used which travel to different locations within a city to deliver packages. So if delivery routes for all these operations are not planned, it will cost millions to Amazon.
Let's say you are currently in Hyderabad, and you have to go to Delhi, Lucknow, and Kolkata. What route you would take?
How many possible routes are there? There are 6 possible routes that you can take. This is the search space of this problem.
The space of all feasible solutions is called search space. Within search space, some solutions will be optimal and some will be non-optimal.
For this problem, the search space is very small, thus we could find the solution very easily. But will you be able to find the best solution if there are a total of 30 destinations? The search space for this problem will have 30! solutions, or 265,252,859,812,191,058,636,308,480,000,000 solutions.
It's not possible to compare each of those solutions for deliveries of just 30 packages. So we need an algorithm that will search this search space for a suitable or best solution.