Bloomberg Tradebook has enhanced its B-SMART trading algorithm with a sophisticated statistical price predictor model (PPM) that further assists traders by automatically adjusting the aggression levels of the algorithm. The enhancement -- B-SMART AUTO -- seeks to statistically do what a trader does - make an assessment of a stock's probable price path using a variety of inputs such as activity on the tape, volatility of the stock, bid/offer spread, as well as peer group and sector analysis.

Depending upon prevailing market conditions and predicted price movements, B-Smart AUTO uses three underlying aggression levels: passive React mode, normal trading and aggressive liquidity capture.

"The Price Predictor Model seeks to create a clone of the trader by making statistically-based decisions of what the trader would likely do if he or she was trading the stock," said Gary Stone, director of trading research at Bloomberg Tradebook, in a company release.

In addition to regulating its aggressiveness, B-SMART AUTO also smart quotes by constantly reassess which venues are most active - placing lit and dark orders in those venues - in an effort to optimize spread capture and avoid being traded around.