In this document, we describe in high-level use cases and strategies to implement machine learning algorithms.

We are implementing machine learning algorithms to provide platform users with benefits such as intuitive selection of loads, carriers, and shippers, trip chaining and revenue maximization, cost prediction, and more.
Machine learning algorithms can only be performed on archived and real-time data. In such cases, users will “opt-in” to allow dexFreight to store and access their historical data.

Download Lightpaper

The document provides a strategic vision for deployment of machine learning within the platform and in no way intended to disclose specific details of algorithm design and implementation. More information on algorithm designs will be made available in our code repository during specific calls for bounty programs.

At dexFreight, it is imperative that ML is part of overall strategy to build a decentralized logistics marketplace. Our mission is to bring benefits of blockchain as well as machine learning technology to logistics companies of all shapes and sizes. In many ways, both machine learning and blockchain will be ubiquitous in the functioning of the platform.

We see a lot of instances where machine learning in logistics is thrown as a buzzword in white papers, trade magazines, and presentations. Through this document, we want to demonstrate to our potential customers and investors that machine learning is not just a buzzword. Instead, it is a critical component of the platform.

About dexFreight

dexFreight is simplifying logistics for a better world with an open logistics market network for freight companies to handle shipments from booking to payment in one place.

For more information, visit www.dexfreight.io

Rajat Rajbhandari, PhD

Written by Rajat Rajbhandari, PhD

CIO and Co-founder at dexFreight