I’m ready to stand up a lean MVP that proves the core value of AnanthaAI’s Customer Insights & Growth Opportunity Agent. The goal is simple: given a bundle of sample customer data, the app should surface the right analytics, predict the next moves, and let a user download ready-to-act segments. Data scope • I will supply (or we can auto-generate) synthetic datasets that imitate CRM, e-commerce, and in-store tables. • At minimum the transactions file must include purchase history. • For feedback we’ll work with three streams—survey responses, online reviews, and customer-support transcripts. Core pipeline 1. Data ingestion & cleaning in Python (pandas preferred). 2. Out-of-the-box analytics: RFM scoring, behavioural segmentation, cohort analysis. 3. Predictive models for churn risk, lifetime value and next-best action—scikit-learn, XGBoost or similar are fine. 4. Streamlit UI that lets a user select a segment, view key metrics, read plain-English recommendations, and export a CSV. 5. Everything containerised or at least runnable with a one-shot requirements file. What I need to see before sign-off • Code repo with clear structure and concise README • Working Streamlit app deployable locally • Synthetic datasets and generation scripts • Short demo video or GIF walking through the UI This build will be shown to early clients and advisors, so polish and reliability matter more than edge-case coverage. If you’ve wired up analytics dashboards or ML-driven recommender flows in the past, I’d love to hear how you’d approach this and the timeline you envision. MVP Objectives The freelancer must deliver: 1. Data ingestion & cleaning pipeline 2. Automated customer analytics (RFM, cohorts, CLV, churn risk) 3. Recommendation engine (growth opportunities) 4. Action-ready output (CSV/Excel segments + insights) 5. UI in Streamlit 6. Documentation + lightweight architecture diagrams --- 3. Project Deliverables A. Data Layer 1. Sample Dataset Creation Freelancer must create 5 datasets: (minimum 10,000 rows each) 1. Customers (ID, demographics, membership, signup date) 2. Transactions (ID, date, SKU, amount, category) 3. Visits/Appointments (for service businesses) 4. Feedback/NPS (scores, comments, dates) 5. Marketing Campaign Data (channels, spend, response)