I have a sizable historical sales dataset and I’d like to turn it into something more forward-looking. My primary objective is to build a reliable model that predicts future outcomes—seasonal demand, product performance, and revenue trajectories—while also extracting the customer behavior signals hidden in the numbers. Here’s how I picture the engagement unfolding: • A clean, well-documented script (Python, R, or similar) that ingests the raw sales data, handles preprocessing, and trains a predictive model. • A concise customer behavior report that highlights segments, purchase frequency, churn propensity, and any surprising correlations you uncover. Visuals in Tableau, Power BI, or matplotlib/Seaborn are welcome if they strengthen the narrative. • Clear hand-off materials: code notebooks, explanation of feature importance, and simple instructions so I can rerun the model with new data. Accuracy and interpretability matter to me as much as raw performance, so please balance advanced techniques (e.g., gradient boosting, random forests) with transparency. If you can wrap the results in a small dashboard or interactive notebook, that’s a bonus, but the essentials are the model and the behavior-focused report. Let me know if you need a sample of the data to scope effort or clarify edge cases before we begin.