A top 10 global telecom company was hemorrhaging margin on international roaming — thousands of bilateral carrier agreements across hundreds of markets, each with different pricing tiers, and routing decisions that depended on manual analysis teams couldn't complete before traffic patterns had already shifted.

ML LABS was engaged through Gigster to design and build a custom ML platform that could analyze roaming traffic worldwide and optimize both cost and routing decisions using time-series models processing ~1TB of new data daily.

What ML LABS Built

The engagement delivered a production ML platform with three core capabilities:

  • Time-series models. Trained on global roaming traffic patterns to forecast demand and cost across markets.
  • Cost optimization engine. Identified the lowest-cost routing paths while maintaining quality thresholds.
  • Routing recommendation system. Adapted to shifting traffic patterns and agreement terms in near real time.

The platform ingested ~1TB of new data daily — live network telemetry, agreement terms, and historical traffic patterns — to produce routing decisions that balanced cost, quality, and capacity constraints across the worldwide network.

Architecture

graph LR
    A["Live Network<br/>Telemetry"] --> B["Streaming<br/>Ingestion"]
    B --> C["Time-Series<br/>ML Models"]
    C --> D["Cost Optimization<br/>Engine"]
    D --> E["Routing<br/>Decisions"]
    E --> F["Network Ops<br/>Dashboard"]

    style A fill:#1a1a2e,stroke:#e94560,color:#fff
    style B fill:#1a1a2e,stroke:#0f3460,color:#fff
    style C fill:#1a1a2e,stroke:#ffd700,color:#fff
    style D fill:#1a1a2e,stroke:#ffd700,color:#fff
    style E fill:#1a1a2e,stroke:#16c79a,color:#fff
    style F fill:#1a1a2e,stroke:#0f3460,color:#fff

The system was built as a production platform for operational teams, not a research prototype:

  • Streaming pipeline ingesting terabytes of daily traffic data
  • Time-series models trained on historical patterns, updated with live data
  • Decision layer producing routing recommendations within latency targets
  • Dashboard for network ops to monitor, override, and audit decisions

Delivery Pattern

The engagement followed ML LABS' standard execution model: define the highest-value target first, ship a working system fast, then iterate based on production feedback.

  • Scoping identified the highest-cost routing corridors as the initial target
  • First deployment covered a market subset to validate the approach
  • Expanded worldwide once models proved reliable under live traffic

Results

Roaming cost per session decreased measurably across targeted corridors within the first quarter. The platform identified optimization opportunities across 128% more corridors than the original scope targeted — surfacing inefficiencies the manual analysis team had never reached. Decision latency dropped from days of manual review to sub-second automated routing. Measured against engagement cost, the optimization delivered over 12x return in the first year.

The platform surfaced 128% more optimization corridors than the original scope targeted — the manual team had never reached them because the data volume made it physically impossible.

The platform became a foundation for the telecom's ML journey across multiple business units. The same architecture pattern — streaming ingestion, time-series modeling, and automated decision layers — was extended to adjacent operational problems.

First Steps

  1. Target the costliest corridor. Find the highest-cost path or most manual decision process and build against that single target first.
  2. Validate under live traffic. Deploy to a market subset and measure cost reduction against the baseline before expanding scope.
  3. Expand after production proof. Scale to additional corridors once the models prove reliable. If an operational routing workflow is already defined, AI Workflow Integration is the direct build path.