Traders at Berkeley recently created their own high frequency trading strategy, acting on 4 stocks traded across 3 markets. However, we have noticed that there has been a large discrepancy between our predicted and realized edge and want to understand where this slippage is coming from. Your goal is to predict the realized edge, or how much Traders is actually earning per trade, and use that information to decide which trades in the test set will have positive realized edge. We have provided relevant information about each trade, explained in the Dataset section. You may use any of the features provided.

Please see [GAME YOSEMITE CLARIFICATIONS](https://docs.google.com/document/d/1B7wEeQ8J0DPXunxw1tIRmUvhrST3LOXcG6bU2YoIK4g/edit?usp=sharing) for additional information on SUBMISSIONS, SCORING, and AUCTION.