Build a Supply-Price Momentum Agent

In this challenge, you will architect a sophisticated real estate intelligence system using Mastra AI (TypeScript) to orchestrate data ingestion and automated machine learning workflows. You will focus on identifying 'divergent' housing markets where building permit growth (Census BPS) is failing to keep pace with home price appreciation (FHFA HPI). To optimize the forecasting component, you will integrate TPOT (Tree-based Pipeline Optimization Tool) via a Python bridge or microservice to automatically discover the best regression models for housing supply trends. The core of the challenge involves building a Mastra AI workflow that processes multi-geographic datasets, calculates momentum indicators, and utilizes an automated ML pipeline to predict future supply bottlenecks. You will define custom tools for the Mastra agent to query Census and FHFA APIs, then synthesize these signals into a 'Market Divergence Score' used by institutional investors to assess local market risk.

• Master the Mastra AI Workflow API to sequence complex data transformation and model inference tasks

• Implement TPOT (Tree-based Pipeline Optimization Tool) to automate feature engineering and model selection for supply forecasting

• Design geospatial joins using GeoPandas or similar libraries to align Census BPS place-level data with FHFA CBSA-level indices

• Build a TypeScript Agent in Mastra that implements custom 'tools' for real-time housing data retrieval

• Orchestrate a cross-language pipeline where Mastra AI triggers Python-based ML optimization via a secure RPC or REST interface

• Optimize data ingestion pipelines for large-scale Census Building Permits Survey monthly and year-to-date files

• Evaluate model performance using Mean Absolute Percentage Error (MAPE) against historical housing cycles