We're seeking a senior product manager to own supply forecasting capabilities that power Amazon's advertising business. Supply forecasting uses statistical sampling of large-scale data sets and predictive modeling to estimate publishers' future inventory availability, enabling programmatic guaranteed ad products and revenue optimization.
Key job responsibilities:
A day in the life:
Your morning starts reviewing overnight forecast accuracy metrics. A key publisher's inventory predictions were off by 15%, and you dig into the data to understand why. You join a working session with applied scientists to evaluate a new sampling algorithm that could improve forecast precision for high-variability inventory. After lunch, you're in back-to-back meetings: first with the programmatic guaranteed sales team discussing how forecast confidence intervals impact deal commitments, then with engineering to prioritize Q2 roadmap items, deciding if we should invest in real-time forecast updates or expand coverage to new publisher types? You spend the afternoon writing a technical spec for seasonal adjustment logic, referencing historical data patterns and proposing model enhancements. Before end of day, you review a dashboard showing how your forecasts performed against actual inventory delivery for last week's campaigns, identifying opportunities to refine your algorithms. You wrap up by preparing talking points for tomorrow's leadership review on forecast accuracy improvements and their revenue impact.
About the team:
You'll join a group of product managers, applied scientists, and engineers focused on predicting publisher inventory availability across Amazon's advertising ecosystem. Our team builds the forecasting systems that enable programmatic guaranteed products, helping advertisers secure inventory commitments with confidence while maximizing publisher yield. We work at the intersection of large-scale data engineering, statistical modeling, and product strategy, tackling challenges like handling billions of inventory samples, accounting for seasonal patterns, and improving forecast accuracy in real-time. The team collaborates closely with yield optimization, sales, and publisher-facing teams to ensure our forecasts drive critical business decisions. We value technical depth, data-driven decision making, and the ability to translate complex analytical problems into practical product solutions.