How ClickPost Is Using Logistics Intelligence Solutions To Reduce Return Rates & Costs

Reports suggest that the logistics sector in India is witnessing an exponential rise. Currently, the size of the logistics industry in India is around $160 billion and with the implementation of GST, it is expected to reach $215 billion by 2020–21 at 10.5% CAGR. 

With such a vision, Delhi-based startup called ClickPost is utilising logistics intelligence solutions to help its customers reduce return rates and costs, provide post-purchase experience and streamline their supply chain operations. 

Founded in 2015, ClickPost is India’s first and Asia’s second-largest integrated logistics platform with more than 100 logistics partners integrated via a single REST API. The company was founded by Naman Vijay and Prashant Gupta who are the alumni of the Indian Institute of Technology, Delhi and National Institute of Technology, Trichy respectively.

Currently, the company is processing more than 8 million shipments per month and growing at a year-on-year rate of 600%. With the help of the logistics intelligence platform, the company has enabled the shippers to have a transparent and more effective way to manage their end-to-end logistics operations. 

Flagship Product

ClickPost provides logistics integration solutions to its customers where the technology is sold as a SaaS product which has 4 levels of tech integration, starting with an ML-driven decision-making engine. The decision-making engine helps select the best logistics partners based on the business objective and the single API then enables integration with all logistics vendors in one place. The next layer helps the e-commerce firms track all their shipments in real-time while identifying and solving any exceptions, predict delays in shipment journeys and commit the correct delivery date to the end customers. And the last one enables its customers to provide easy returns.

The company has also its failed delivery intelligence suite which leverages a large amount of data in the system to help reduce RTOs in e-commerce. This suite works by predicting the best way to get customer feedback on failed deliveries and communicate the same to logistics partners. 

Use of AI And ML

The main focus of the company is to use Machine learning to predict the correct delivery date allows the users to set the correct expectations with the logistics partners as well as their consumers. According to Vijay, the company uses various ML algorithms like multiclass classification and regression models to solve complex problems like predicting the route of the shipment and identifying potential delays in the shipment journey. It has also built proprietary models on top of the data to predict the estimated delivery date.

Tech Stack

The core tech stack of ClickPost is built on Python. It uses Kafka and Spark to process huge amount of collected data and run analytics on top of that. In order to build, train and deploy the ML models, the company uses platforms like SageMaker. Further, the company has a reporting platform built internally over S3 which is able to deliver reports in realtime to the customers with current data. 


Currently, ClickPost captures the data across the shipment lifecycle and helps customers with workflows to manage. While asking for the future roadmap, Vijay replied that the company is building more AI-driven features to help the clients predict exceptions in the supply chain as well as solving them intelligently. Further, the company is trying its level hard to expand its services to other geographies and build visibility there. 

In terms of expanding from within, the company always looks at hiring candidates who wish to solve challenges at scale while having the freedom that comes with working in a startup.

More Great AIM Stories

Ambika Choudhury
A Technical Journalist who loves writing about Machine Learning and Artificial Intelligence. A lover of music, writing and learning something out of the box.

More Stories


8th April | In-person Conference | Hotel Radisson Blue, Bangalore

Organized by Analytics India Magazine

View Event >>

30th Apr | Virtual conference

Organized by Analytics India Magazine

View Event >>

Yugesh Verma
All you need to know about Graph Embeddings

Embeddings can be the subgroups of a group, similarly, in graph theory embedding of a graph can be considered as a representation of a graph on a surface, where points of that surface are made up of vertices and arcs are made up of edges

Yugesh Verma
A beginner’s guide to Spatio-Temporal graph neural networks

Spatio-temporal graphs are made of static structures and time-varying features, and such information in a graph requires a neural network that can deal with time-varying features of the graph. Neural networks which are developed to deal with time-varying features of the graph can be considered as Spatio-temporal graph neural networks. 

Vijaysinh Lendave
How to Evaluate Recommender Systems with RGRecSys?

A recommender system, sometimes known as a recommendation engine, is a type of information filtering system that attempts to forecast a user’s “rating” or “preference” for an item. In this post, we will look at RGRecSys, a library that performs constraint evaluation of recommender systems.

3 Ways to Join our Community

Discord Server

Stay Connected with a larger ecosystem of data science and ML Professionals

Telegram Channel

Discover special offers, top stories, upcoming events, and more.

Subscribe to our newsletter

Get the latest updates from AIM