Develop Time-Series Forecasting Model

Build a time-series forecasting model (e.g., ARIMA, Prophet, or a simple neural network) that predicts the price of a chosen critical mineral for the next 30 days. Your model must incorporate the sentiment scores and entity information extracted by the LangChain/Yi-34B pipeline as exogenous variables. Justify your choice of model and describe your feature engineering process. How will you evaluate the model's accuracy?