In the past decade, supply chain management has skyrocketed across verticals. With e-commerce becoming a critical economy booster, its success depends heavily on an efficient decision-making platform.
With advanced technology solutions making steady inroads into businesses every day, the era of supply chain management has evolved. Several companies are thriving today as they capitalize on a robust technology architecture to support large-scale supply chain operations, and are providing analytical insights on route optimization freight tracking and analytics, sales beat optimization.
Locus is a state-of-the-art decision-making platform for logistics, optimizing a range of operations to provide consistency, efficiency & transparency. The company works with several entities that include Blue Dart, Urban Ladder, TATA Group, and KOEL, among others. It factors various business rules and methods using technologies for multiple variable elements like SLAs, traffic delays, and capacity constraints while planning and dispatching orders in areas like FMCG, retail, 3PL, e-commerce and home services to name a few.
The company recently did projects for logistics major Blue Dart, home service player Droplet and e-commerce player, Myntra.
They identified manual shipment processing as a challenging area, which can significantly increase error rates, with higher processing time and human resource cost. Manual shipment sorting attributes to reduced time on the field to deliver and lack of accurate checks for mis-routes. Conventional operational methods can lead to additional overhead costs, adversely affecting delivery efficiency and compromise on agreed service levels with end customers.
For Blue Dart, Locus automated the sorting process at last-mile delivery hubs per predefined routes and optimized resources at the hub. Currently, sorting methods for shipments are automated, enabling Blue Dart to save a sizeable portion of their sorting time. For Myntra, the company leveraged data-driven insights to create the best possible routes to visit vendors. Routes were designed to ensure that time slots for individual vendors are met, and the time taken to return to the mini-hubs is kept to a minimum.
Droplet, on the other hand, is using Locus’ route optimization – an intelligent route planning suite that generates optimal & profitable delivery routes along with an efficient resource utilization plan.
The Use of AI to Map Out Efficient Routes
Locus has developed geocodes for each address with high precision, found the region the address is in, and assigned the route number or delivery boy who will serve that region.
Geocoding requires a combination of techniques like Natural Language Processing (NLP) and LSTM models to understand the Indian addresses. They also built a context-aware confidence scoring model that informs if geocoding is accurate or if more information is needed. Prototyping was done in Python with libraries like NLTK and Sklearn, among others. Keras was used for neural networks and LSTM. Java was used in the production environment.
Locus provided the following solutions:
● Geocoding: Efficient geocoding of addresses to ensure they are mapped against the corresponding route number irrespective of the quality of address, leaving no room for error.
● Automated Route Allocation: Routes provided by Intellisort can be printed on the shipping label to eliminate the local intelligence & manual dependence.
● Route Optimization: Factors in real-time traffic, dynamic business constraints that help increase the execution of deliveries at a reduced cost. Traditional approaches depend on human intelligence, which can lead to an increase in sorting time and expenses.
Tangible & Profitable Impact Thanks To AI
For Blue Dart, sorting time was reduced significantly. There was a reduction in the number of people deployed for the entire sorting process while delivering a high route mapping accuracy. In addition, accurate detection of misrouted shipments allowed the team to take necessary corrective steps.
For Droplet, cost of operations reduced by 30%, while SLA compliance improved by 13.5%.
“Traditionally, organizations tend to rely on human intelligence for decision making, believing it to be their best resort. However, we found out that a lot of times, human decisions can be intuitive and not backed by any proper data or logic. We realized that automating the process via data-driven technology can not only help in improving efficiency; it can also help the persons involved in the process of making decisions.”
– Shantanu Bhattacharyya, Data Scientist, Locus
This is part of our ongoing series Innovate2Transform, where we bring to you the leaders of the industry talk about the latest in innovation, technology and trends in their industry sectors.
If you want to contribute, write to firstname.lastname@example.org.