How a US Chemicals Multinational Transformed Its Railcar Logistics Using Decision AI: $2.5M+ Saved & $1.56B in Revenue Protected
Overview
A multinational U.S. chemicals manufacturer, ships chlorine — a high-risk, time-sensitive product — across the country to 100+ customers using a fleet of 1,200 leased railcars from 8 locations. Unlike many other commodities, chlorine cannot be produced and stockpiled. It must be transported almost immediately after it’s manufactured, making the availability and circulation of railcars critical to production continuity and revenue realization.
The multinational’s logistics, operations, and plant teams were under pressure to manage rising costs, improve delivery reliability, and reduce railcar stock & idle time — all without compromising safety or compliance.
The Challenge
The chemicals multinational needed to answer three foundational questions:
- Where Are My Railcars? Without live tracking, the team lacked clarity on fleet location, staging status, or unloading progress.
- Are the Railcars Empty or Full? Whether it was at their plant sites or at customer locations, they needed to know the stage of processing that the railcars were in to orchestrate loading or reverse pickups effectively.
- When Will My Railcars Return? Planning chlorine production depended on knowing when each railcar would be back and ready for reuse.
- Can I Do More With Fewer Railcars? Each additional leased railcar added to maintenance, cleaning, and parking costs — and made the network harder to manage.
What They Tried & Why It Didn't Work
- ERP, TMS & WMS Modules: Data entry was manual, lagging, and non-actionable. These systems couldn’t provide real-time location or shipment status.
- Rail Tracking Portals: They only provided information on trains and not on individual railcars. Further this information was not real time & late by days or months.
- Track & Trace Solutions: Most failed on multiple fronts — tracker installation was complex, location accuracy wasn’t tight enough to distinguish between loading/unloading zones in a facility, and devices weren’t ruggedized for harsh rail environments.
As a result, the multinational couldn’t reduce the number of railcars in circulation, predict railcar returns, or optimize delivery scheduling.
Enter Decklar’s Real-Time Decision AI with Visibility
The chemicals multinational deployed Decklar to optimize all 1,200 railcars, combining “always on” GPS-powered solar trackers with Decision AI to move from observation to action.
- Trackers provided live, reliable data across rail yards, customer sites, and in transit
- Decklar integrated with the multinational’s transport systems
- Each railcar’s full trip was monitored — from loading to unloading to return
- AI analyzed unloading durations and dwell times, predicting return ETAs and helping improve circulation planning
- Custom dashboards were designed for both frontline & operations teams, enabling user-level engagement and decision support
Day 1: Real-Time Railcar & Shipment Visibility
Within 8 weeks, the multinational had visibility into:
- Where each of the 1,200 railcars were — in a yard, en-route, or at a customer site
- When a shipment entered the customer facility and when unloading began
- Electronic Proof of Delivery (ePOD) events and digital timestamps
- Which cars were idle and how long they had been stationary
This enabled site and ops teams to respond faster, eliminate manual checks, and begin measuring turnaround more systematically.
Day 2: Decision AI Optimized Railcar Fleet Performance & Aligned Production Plans
By month three, Decklar’s Decision AI began delivering deeper value:
- Predicting Empty/Full Status: AI analyzed patterns at the multinational’s and customer’s rail yards to determine whether the railcar was empty or full based on micro-location intelligence within the facility.
- Cycle Time Forecasting: Predicted when each railcar would return based on customer unloading patterns and route performance.
- Fleet Reduction Recommendations: Enabled the multinational to reduce leased railcars by optimizing circulation — fewer railcars, same delivery volume.
- Cleaning & Parking Cost Avoidance: Fewer railcars meant fewer cleaning cycles, less yard congestion, and reduced parking charges.
- Role-Specific Dashboards: Delivered AI-powered role-specific insights to operators, logistics managers, and plant planners that could be constantly modified based on the decision intelligence they were seeking.
- Production Alignment: With predictive visibility into railcar positioning, chlorine production could be aligned with delivery and return timing — minimizing disruption risk.
Why Decision AI with Visibility Was Needed Together
The combination of Decision AI and Visibility was essential because visibility alone showed where railcars were — but not whether they were being unloaded, when they’d return, or how to rebalance fleet usage. Decision AI alone lacked real-time, high-accuracy location data to correctly interpret cycle performance and predict risk. Together, they helped the chemical multinational shift from reactive shipment tracking to predictive rail logistics — cutting costs, protecting output, and minimizing safety risks.
ROI Summary
Direct Benefits:
- Railcar Inventory Reduction: 1.6M/year
(Leasing cost of $1,485/month/railcar × 90 railcars reduced) - Cleaning & Maintenance Cost Avoidance: 600K/year
- Parking Cost Reduction: $250K/year
- Labor Savings from Manual Reconciliation: $300K/year
- Protected Revenue from Availability of Railcars: $1.56B/year by using continuous flow of Chlorine
Indirect Benefits:
- Chlorine production continuity and revenue assurance
- Improved railcar cycle count and throughput
- Enhanced safety and compliance from reduced idle risk
- Fewer missed shipments due to railcar unavailability
Total Estimated Impact:
$2.5M+ in annual logistics cost savings, plus $1.56B in revenue protected
Summary
By combining Decklar’s real-time visibility with its Decision AI engine, the US chemicals multinational company transformed its chlorine railcar network into a leaner, faster, and more predictable operation. With improved railcar utilization, fewer idle assets, and smarter planning, the company lowered logistics costs by millions while improving production continuity and protecting billions in revenue — all without increasing fleet size. Decklar delivered not just data, but decisions — enabling it to run rail logistics like a strategic asset, not just a cost center.
Request a Personalized Demo to see it in action.