Contact Now
← Back to freelance work
Logistics2025 · 8 weeks

A Logistics Company in Lucknow

Built a delivery package ETA prediction model to give customers more accurate delivery windows.

Headline Result

Cut ETA prediction error by 29% compared to the previous static estimate.

Timeline
8 weeks
Industry
Logistics
Core Stack
Python, XGBoost

01.The Challenge

Shipment ETAs were calculated from a flat distance-and-speed formula that ignored real-world variables like traffic and weather delays.

02.The Solution

Built a prediction model incorporating route history, weather, and customs data to generate dynamic, continuously-updating ETAs. Rather than a full platform rebuild, the fix was scoped tightly around Freight & Logistics's actual bottleneck, which kept both timeline and cost down.

03.How It Went

  1. 1Kicked off with a series of short conversations with the Freight & Logistics team to understand the workflow the new system would actually need to fit into.
  2. 2The first working version for Freight & Logistics came together quickly using Python, which left more time for testing edge cases in their data.
  3. 3Ran the first version alongside Freight & Logistics's existing process for a few weeks rather than replacing it outright, to build confidence before full cutover.
  4. 4Set up basic monitoring so Freight & Logistics's team would know quickly if performance started drifting, rather than finding out from a downstream complaint.

04.Results

  • Cut ETA prediction error by 29%
  • Reduced customer support inquiries about shipment status
  • ETAs now update automatically as delivery package progress (moves).
  • Set up with basic monitoring so Freight & Logistics's team would catch any drift early, not after it became a problem

“For our company, it felt less like hiring a contractor and more like adding someone to the team for a few weeks.”

— COO, A Freight & Logistics Company in Lucknow