About this role
inDrive's Forecasting product turns large-scale marketplace data into daily and monthly forecasts of the company's core supply, demand and financial metrics. These forecasts are the backbone of target setting, financial planning and scenario analysis for business teams and leadership. We are looking for a Senior Analyst to own this product: the quality and credibility of the numbers, the planning processes they feed, and the story behind every deviation. You will take over a working production solution (Python, BigQuery) and keep it reliably serving the business — but the core of the role is not modeling for its own sake. It is understanding how the business works: how pricing, incentives, marketing and market events move metrics, how those metrics connect to each other, and what decision-makers need from a forecast to plan with confidence. Business & planning Own the forecast as a decision-making product: track plan vs actual, decompose variances into business drivers (seasonality, pricing, incentives, marketing, external events), and explain in business terms why the numbers changed Support company planning cycles: provide forecast baselines for target setting and budgeting, and align assumptions with finance and business stakeholders Build and run scenario ("what-if") analysis for planned interventions: pricing changes, incentive and marketing spend, product launches, market expansion Maintain the dependency logic connecting supply, demand and financial metrics, so that forecasts stay mutually consistent and aggregate correctly across markets Translate ambiguous business questions into measurable forecasting problems; communicate assumptions, uncertainty and limitations clearly to both business and technical audiences Forecast production Run and monitor recurring daily and monthly forecasts: data completeness, sanity checks, run-over-run drift Investigate anomalies end to end — from inputs and business transformations to forecast outputs — getting to the business reason, not just a technical fix Improve models pragmatically: baselines, honest validation, and model choices driven by measurable planning value rather than sophistication. Keep the solution maintainable: readable Python, documentation, versioned changes