The micro-price is a weighted average between the bid and ask prices, where the weight is a simple function of the bid and ask sizes. The micro-price is a good predictor of future mid-price moves and is frequently used by high frequency trading algorithms to make micro-decisions, such as whether to cancel, submit a limit order or a market order. However, not much effort has been made in determining whether the micro-price is a fair or efficient price. We redefine the micro-price as the limit of a sequence of expected mid-prices at future stopping times. We provide conditions for this sequence to converge. Volatility signature plots using this notion of micro-price indicate that our method is an effective method for filtering out microstructure noise. Speaker(s): Sasha Stoikov (Cornell University (NYC))