social share alt icon


MPHASIS.AI ENABLES GLOBAL LEADER IN LOGISTICS TO ACHIEVE GLOBAL HARMONIZED CLEARANCE (GHC) OF WORLDWIDE OPERATIONS

CLIENT

 

Our client is an American multinational conglomerate and a leader in the business of transportation, e-commerce, and business services. As an industry it provides rapid and reliable services in more than 220 countries, connecting markets that comprise more than 99 percent of the world's GDP.

THE REQUIREMENT

The client was seeking to enhance various aspects of GHC services including preparation, brokerage, customer profiling, screening and interception, in-bond management, and admissibility.

SOLUTION

 

Automation of clearance processes play a critical role in seamless movement of goods across borders to significantly facilitate trade. Through value stream mapping of clearance operations leveraging AI solutions, logistics companies can bring in significant efficiency gains.

Mphasis first created an effective value stream mapping of the client’s global clearance operations, and automated the business services in the following areas:

  • Contract event consumer services

  • Import clearance location identification

  • Customer matching

  • Harmonized code identification

  • Shipment classification

  • Sanity rules evaluation

  • Team, shipping, and competency assignment

  • Declaration evaluation

  • Ancillary charges computation

  • Billing

  • Customer contact identification


We further identified the potential for AI/ML interventions in different areas of establishing clearance data and execution of clearance operations - such as customer profile matching to identify likely customers, creating broker productivity toolbox, developing risk profiles for customers, auto work queue prioritization, developing broker scorecards, automation of admin tasks such as power of attorney validations, etc.

Specifically, we used deep learning, NLP, object detection, fuzzy search, supervised ML, for data extraction from commercial invoices (AWB number, shipper information, commodity description, HS codes), HS code mapping by analysis of historical shipment data and prediction of caged shipments. We also leveraged generative AI for matching based on rule books or historical data, and customer chats.

Additionally, we created a HS code predictor and data-driven recommender system that would enable the client to understand and relate the user-provided description with the rules book.

BENEFITS

 

Our efforts and solution enabled the client to

Better understand and relate user-provided descriptions with the rule book

Align seamlessly with historical best practices

Improve and increase productivity of processes