I have a collection of CSV/Excel files already cleaned into several data.frames. The first step is to turn this raw information into an interactive PowerBI dashboard focused on descriptive analysis. I need to surface the classic statistical insights—promedios y medias, mediana y percentiles, and desviación estándar y varianza—so that any stakeholder can quickly understand how the data is distributed. Once the dashboard is in place, I then want to move on to two machine-learning components: • A supervised predictive model that can forecast the main KPI I will share with you once we start. • An unsupervised clustering model that segments the records into meaningful groups for later marketing actions. Please work in PowerBI for the visual layer and feel free to use Python (pandas, scikit-learn) or R (tidyverse, caret) for the modeling—whichever you prefer, as long as everything connects smoothly back into PowerBI. Deliverables 1. PowerBI .pbix file with fully interactive visuals and filters. 2. Clean, well-commented code/notebooks for both the predictive and clustering models. 3. A short deployment guide showing how to refresh the data from the original CSV/Excel sources and update the models. The project wraps up when I can refresh the files, the dashboard updates, and both models retrain without errors.