Dr. Kevin Seppi

Dr. Kevin Seppi, director of the Applied Machine Learning Laboratory, and master's student Patrick Mullen, developed an algorithm that will allow online businesses to map dynamic pricing and optimize their earnings.  The algorithm, known as the particle swarm optimization model, compares market prices to particles.  The particles, or prices, gravitate to the optimal level and stay there until a better option becomes available.  All businesses are looking for that place where they make the most profit, but finding it means testing the waters, setting experimental prices, and monitoring market reactions.  Unfortunately for businesses, this experimentation often means losing time and money. 

However, the particle swarm optimization model allows businesses to set a price that maximizes revenues without having to go through the costly and time-consuming experimentation process.

One important aspect of the model created by Seppi and Mullen is that it accounts for the unpredictable.  The model looks at unpredictable factors, such as market change and environmental noise, as it determines optimal prices.  In effect, they have created an algorithm which thinks and learns as the market moves around it.

In their research, Mullen and Seppi tested the algorithm using five market patterns: a constant market, an up trend, a down trend, a random market, and an intervention, or suddenly changing, market.

Dr. Seppi hopes that this research will help not only businesses, but also consumers and the economy as a whole by making the economy fundamentally more efficient.