Design a machine learning system to predict stock prices. What data sources would you use, and how would you process this data?
Instruction: Detail your approach, including data collection, preprocessing, and model selection.
Context: This question tests the candidate's understanding of financial market predictions using machine learning, with a focus on data handling and model architecture.
Updated
Official answer available
Read the opening below, then unlock the full answer and practical guidance.
I would start by reframing the problem slightly, because a return, direction or volatility target may better match a particular decision than the absolute price level; the choice depends on the use case...