Download PDF

Nextbillion.ai > Case Studies > Intuitive Freight Tracking Enhances ETA Accuracy for Indian Logistics Firm

Intuitive Freight Tracking Enhances ETA Accuracy for Indian Logistics Firm

Technology Category

Analytics & Modeling - Machine Learning
Robots - Autonomous Guided Vehicles (AGV)

Applicable Industries

Automotive
Transportation

Applicable Functions

Logistics & Transportation
Warehouse & Inventory Management

Use Cases

Last Mile Delivery
Vehicle Performance Monitoring

Services

Cloud Planning, Design & Implementation Services
System Integration

The Challenge

A leading Indian logistics tech company, known as the country’s largest neutral freight network, was facing challenges in providing an intuitive freight tracking experience for their customers. The company was operating in a complex industry with low tech adoption at different levels. The primary challenges included tracking thousands of data points for each journey, such as accurate routing across highways, country roads, and warehouse locations, traffic data across cities and states, setting up contextual POIs, and additional data such as tire wear-and-tear, vehicle utilization, tolls, and permits. These data points were managed by different stakeholders, causing significant operations challenges. The second challenge was accounting for local nuances like vehicle restrictions & driving behavior, which varied tremendously from state to state in India. Other complications included the type of vehicle, changing topographies, driving patterns, and speed limit depending on the cargo.

About The Customer

The customer is a leading Indian logistics tech company, renowned as the country’s largest neutral freight network. They operate in a complex industry with low tech adoption at different levels. The company manages thousands of data points for each journey, including accurate routing across highways, country roads, and warehouse locations, traffic data across cities and states, setting up contextual POIs, and additional data such as tire wear-and-tear, vehicle utilization, tolls, and permits. They also have to account for local nuances like vehicle restrictions & driving behavior, which vary tremendously from state to state in India.

The Solution

The solution involved analyzing the company’s historical freight and navigational data, and running it through machine learning models. This process provided valuable insights into the nuances of the problem. A custom solution was created using a blended-AI approach that could keep up with the challenges of the logistics industry while helping the client thrive. This solution efficiently tackled local conditions, unstructured addresses, varied vehicle types, and unique driving behaviors, helping their solution make informed predictions of the route likely to be taken by drivers and the corresponding ETAs. A 5-step approach was crafted, which included map data curation, AI inferences, routes and ETA modelling, shadow testing, and finally going live with the new solution. The custom map stack was set up on the customer’s cloud by leveraging Kubernetes.

Operational Impact

The new intelligent mapping solution significantly improved the organization's operations. It resulted in a mapping ecosystem that was completely tailored to the organization’s drivers’ and tech team’s requirements. It directly factored the operational data and allowed an additional layer of easy customizability on top of it, allowing the client to account for changes rapidly without being dependent on their map provider. The solution also led to an overall increase in throughput, the ability to auto-scale up or down depending on the business’s demands, end-to-end control over the new map stack, a decrease in the cloud ingress/egress bills due to the API calls being served on-prem, and no IP leakage as a result of self-hosting. The company was able to reduce the safety risk of drivers and freight by extracting hidden operational insights like driving patterns of long-haul journeys such as tolls, rest stops, and transit point information. They were also able to attain seamless loading and unloading by integrating all internal data directly onto the map, optimal routes based on specific vehicle type through custom routing APIs, and enhanced product experience through precise location information.

Quantitative Benefit