Demand and audience forecasting for financial and media clients (Artefact)

I worked on 2 consulting projects in parallel. A media group needed forecasts of audience reach and CPM, the advertising cost per 1,000 impressions. These forecasts supported advertising inventory plans. Meanwhile, a financial services client needed transaction forecasts for liquidity and capital planning.

Each project allowed 2 weeks from kickoff to an executive demo. This left little time to investigate the data. Moreover, some ad placements had sparse histories, while niche financial products had few records. When forecasts challenged client expectations, I had to explain the results immediately. At the same time, I led both the technical work and stakeholder discussions.

In each 2-week sprint, I handled data gaps, selected models, and added revenue and reporting constraints. Meanwhile, I wrote handoff documents. Then I translated forecasts into planning terms that senior leaders could use.

I delivered a model card describing the model, a feature dictionary, a retraining protocol, and a dashboard guide. Before sign-off, client teams compared the outputs with their knowledge. Then we resolved any differences together.