I have a sizable set of raw financial data that needs to be turned into clear, decision-ready insight. The job covers three linked pieces of work: cleaning and structuring the data, applying the right machine-learning techniques to surface patterns or predictive signals, and packaging the results inside an interactive report that stakeholders can explore on their own. Scope and expectations The data arrives in monthly batches (CSV and XLS) spanning revenue, cost, and balance-sheet metrics. I need a robust pipeline—Python, R, or a notebook environment is fine—that ingests these files, handles missing values, and standardizes the fields. From there, build and validate models that can flag anomalies and forecast key indicators (AR, cash flow, or any other variables you think add value). Finally, present everything in an interactive report; I’m open to Power BI, Tableau, or a web app using Plotly Dash/Streamlit, so long as executives can slice and drill without installing extra software. Deliverables • Clean, documented dataset (with reproducible ETL code) • Machine-learning notebooks/scripts with comments explaining methodology and metrics • Fully functional interactive report hosted or packaged for easy deployment • A brief hand-over walkthrough (recorded or live) How to stand out Attach a detailed project proposal that sketches your planned workflow, proposed algorithms, and timeline. I’m less interested in a résumé and more interested in seeing how you’ll tackle this specific challenge. If you have a short demo link to a past interactive financial report, feel free to include it. I’m ready to move quickly once I see an approach that fits, and I’m happy to answer technical questions before we start.