I have a large collection of historical financial figures that I’m struggling to translate into clear, actionable intelligence. I need a machine-learning workflow that turns this raw numerical data into readable patterns, forecasts, and concise dashboards. Here’s what success looks like for me: • A cleaned and well-documented dataset (Python / pandas) • At least one predictive model—regression, time-series, or another method you justify—built and trained in scikit-learn or TensorFlow • A short report explaining the model’s performance, key financial insights uncovered, and any limitations • Reproducible code, saved in a Git-friendly structure, so I can rerun the analysis with fresh data later I will supply the data and any domain context you need. Please bring experience handling financial data quirks (missing entries, outliers, non-stationarity) and be comfortable explaining your choices in plain language. If you have examples of previous financial analytics work, even better—share them and let’s get started.