HomeWorkAboutArticles Let's Talk →
← Back to all work
ML & Forecasting · Multi-market

Demand Forecasting
& Control Tower

A proprietary ML model generating 4-week, hourly-granularity demand predictions — integrated with a real-time capacity alert system and deployed across India, GCC, and Japan. Built to replace the spreadsheet-and-intuition approach that was costing thousands of manager hours and leaving capacity decisions to guesswork.

17%
Forecast accuracy
improvement
6,000+
Manager hours
saved per year
4
Markets on one
unified platform

Capacity planning was running on gut feel and spreadsheets

Before the control tower, demand planning at Amazon's quick commerce operation was a manually intensive, market-by-market exercise. Each market had its own approach — some using statistical models, some using historical averages, some running purely on operations manager intuition.

The compounding problem: quick commerce is uniquely hard to forecast. Unlike standard e-commerce where demand curves are relatively smooth, same-day delivery demand spikes sharply around meal times, weather events, local holidays, and even sports matches. A model calibrated on weekly averages is systematically wrong at hourly granularity.

The consequence of under-forecasting: capacity constraints during peak windows, SLA misses, driver shortages. The consequence of over-forecasting: idle capacity, inflated cost base. Both were happening, in different markets, on the same day.


4-week horizon, hourly granularity — the signals that matter

The forecasting architecture I built combines four signal classes, weighted differently for each market based on the dominant demand drivers:

Signal 01
Historical demand patterns
Hourly order volumes from the past 52 weeks, seasonality-adjusted and decomposed by day-of-week and time-of-day
Signal 02
External event calendar
Local public holidays, sports events, weather forecasts, and promotional calendars — major demand amplifiers in GCC markets
Signal 03
Real-time capacity state
Live FC throughput, fleet availability, and driver supply — fed back into the forecast to flag when predicted demand exceeds current capacity ceiling
Signal 04
Category-level demand mix
Not just total orders — but the mix of grocery, electronics, and essentials, because different categories have different pick times and weight different bottlenecks
Architecture decision
I pushed for a unified model across all 4 markets rather than separate market-specific models. The counterargument — market differences would reduce unified model accuracy — was valid. But separate models also mean separate data science resource requirements, separate retraining cycles, and four sets of model drift to monitor. A single platform with market-level feature weighting proved the right balance: 17% accuracy improvement, without the operational overhead of four independent systems.

From forecast to action — the real-time alert layer

A forecast sitting in a spreadsheet helps no one. The control tower product is the operational layer that turns forecasts into actions:


The numbers

ML ForecastingS&OPControl TowerReal-time AlertsCapacity PlanningMulti-marketData Products

Other projects from this era

Based in Dubai · Open to select roles